Back to Search
Author profile
Affiliations
Documents
Optimization of encoders and receiving systems for machine analysis of coded video content (Draft 10)
AHG9: Bug fixes for multiple prompts in NNPF SEI messages
AHG9: Bug fixes of NNPF SEI messages in TuC document
AHG9: On quality metrics SEI message
AHG9: Transcoding history information SEI message
AHG9: On temporal extrapolation semantics in EOI SEI message
AHG9: On indication of intermediate data application in EOI, SPO and NNPFC SEI messages
AHG9: On shutter interval information SEI message
Non-EE2: Temporal CABAC and CTPI at Different CTU Locations
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
EE2-3.3 Intra LfnstIdx Prediction
AHG9: Historical Information SEI message
EE2-5.1: Counter-based Temporal Probability Initialization (CTPI)
AHG9: On temporal sublayer limitation in EOI SEI message
AHG9: On consistency of ViewId and NumViews in the SEI messages
AHG9: On consistency of maximum number of temporal sub-layers in the SEI messages
AHG9: Editorial improvements for VSEI v4 and TuC
Suggested changes on Draft ISO/IEC TR 23888-3
[Non-EE2] Intra lfnstIdx Prediction
AHG12: Tensor-Based Intra Mode Derivation in VTM and JVET-AN0267 software
Non-EE2: Counter-based Temporal Probability Initialization for Temporal CABAC
AHG9: Additional auxiliary picture type to support V-PCC bitstreams
AHG9: On quality metrics SEI message
AHG9: On picture generation method indication in encoder optimization information SEI message
AHG9: On reserved zero bits semantics
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
AHG9: Extensions of decoded picture hash (DPH) SEI message
AHG9: On layer identifier range and number of layers information in the SEI messages
AHG9: Decoder post-processing information SEI message
AHG9: On SEI message semantics for human viewing and machine analysis
AHG9: Temporal resampling information SEI message
AHG9: Spatial and bit depth restoration SEI message
AHG17: Description of NNVC-based CfE response
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
On Intra Period of Random Access Test Case for HD and below Content
Suggestions on GOP Size Setting of Random Access Configuration for Live-streaming Applications
AHG7: TMRL Tool-Off Bug Fix
AHG12: Fix on cabac_init_flag and Temporal Cabac Inheritance
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
Optimization of encoders and receiving systems for machine analysis of coded video content (Draft 9)
Optimization of encoders and receiving systems for machine analysis of coded video content (Draft 8, for future updates)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
EE1-3.3 – NNVC-VLOP3 retraining adding BVI-AOM
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
Optimization of encoders and receiving systems for machine analysis of coded video content (Draft 7)
Common test conditions and evaluation procedures for neural network-based video coding technology
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
AHG8: Tool development status on Optimization of encoders and receiving systems for machine analysis of coded video content
Update of JVET common test conditions and evaluation procedures for neural network-based video coding technology
AHG8: Joint teleconference with WG 4 AHG on Video Coding for Machines
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG8: Missing curve-fitting part
Optimization of encoders and receiving systems for machine analysis of coded video content (draft 6)
Common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
Common test conditions and evaluation procedures for neural network-based video coding technology
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
Optimization of encoders and receiving systems for machine analysis of coded video content (draft 5)
Common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG8: Updates for technical report
AHG9: Bit-depth truncation as optimization type in EOI SEI message
EE1-3.1: Deep Reference Frame Generation for Inter Prediction Enhancement
Optimization of encoders and receiving systems for machine analysis of coded video content (draft 4)
Call for training materials for neural network-based video coding tool development
Proposed text for a Call for training materials for neural network-based video coding tool development
AHG8: Truncating bit depth in video coding for machine tasks
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Neural network-based video coding (AHG11)
EE1-1.1: Report on training with HOP architecture change for EE1-0 (variant 1)
EE1-1.4: Joint design of rotation and flipping on NNLF
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
EE1-3.1: Deep Reference Frame Generation for Inter Prediction Enhancement
[AHG8] Comments and editorial changes to the draft TR on optimizations for encoders and receiving systems for machine analysis of coded video content
Common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
Common test conditions and evaluation procedures for neural network-based video coding technology
AHG8: A temporal resampling algorithm
AHG12: SbTMVP with MMVD
AHG11: Decoder complexity optimization for NNVC in-loop filter
AHG6: Encoder memory profiling on ECM software
AhG11/EE1: Status of the joint EE1-0 (LOP.2) training
EE1-1.2.3: Input and output rotation of model for NNVC in-loop filter
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
EE1-2.1: Deep Reference Frame Generation for Inter Prediction Enhancement
EE1-1.1.5: Combination test of EE1-1.1.1 and EE1-1.1.2
AHG6: On ECM SW memory consumption
EE1-1.1.1: Optimization for complexity-performance trade-off of HOP network
[AHG9] Inter Picture Dependency SEI message
AHG8/AHG9: Truncated bit depth support SEI messages
Optimization of encoders and receiving systems for machine analysis of coded video content (draft 3)
Common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
Common test conditions and evaluation procedures for neural network-based video coding technology
On ECM SW memory consumption
AHG11/AHG14: Fix MS-SSIM calculation for SR
AHG11: Input and output rotation of model for NNVC in-loop filter
EE1-1.5: Optimization for complexity-performance trade-off of HOP network
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
EE1-5.1: Deep Reference Frame Generation for Inter Prediction Enhancement
AHG8: Improvements of the BD-rate model using monotonic curve-fitting method
Optimization of encoders and receiving systems for machine analysis of coded video content (draft 2)
Common test conditions and evaluation procedures for neural network-based video coding technology
Common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
EE2-2.5b: Combined test of Test 2.2 and Test 2.3
AHG8: Update on TVD object tracking dataset
AHG9: On extensibility of NNPFC purpose bitmask
EE1-1.7-related: Combination test for NNVC based on filter set 0
AHG11: Unified NNLF solution for high operation point
On Common Test Conditions document
EE2-2.3: SbTMVP with MMVD
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG8: VVC tool analysis for Machines Vision Tasks
EE1-1.7: Optimization of training and network for NNVC filter set 0
EE1-2.1-related: DRF Model without QP Input
EE1-2.1: Deep Reference Frame Generation for Inter Prediction Enhancement
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
[AHG8] Proposed text for optimization of encoders and receiving systems for machine analysis of coded video content
Common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
Optimization of encoders and receiving systems for machine analysis of coded video content (draft 1)
Common test conditions and evaluation procedures for neural network-based video coding technology
EE2-2.7: Enhanced temporal motion information derivation
EE1-related: Combination of EE1-1.1 and EE1-1.2
Non-EE2: SbTMVP with MMVD
EE1-1.1-related: More refinements on NN based in-loop filter
EE2-3.8: Combination of chroma IBC tests
EE1-1.2: encoder-only optimization for NN based in-loop filter with a single model
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Low latency and constrained complexity (AHG7)
EE1-2.2: GOP Level Adaptive Resampling with CNN-based Super Resolution
AHG15: On common test conditions for optimization of encoders and receiving systems for machine analysis of coded video content
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG15)
AHG11: Deep Reference Frame Generation for Inter Prediction Enhancement
EE1-1.1: More refinements on NN based in-loop filter with a single model
EE2-3.7: Chroma IBC method as in VTM-5.0
[AHG15] Draft technical report on optimizations for encoders and receiving systems for machine analysis of coded video content
Common Test Conditions and evaluation procedures for neural network-based video coding technology
Crosscheck of JVET-AB0118 (EE2-2.5a: Enhanced temporal motion information derivation)
EE1-2.3 related: GOP Level Adaptive Resampling with CNN-based Super Resolution
Preliminary draft of algorithm description for Neural Compression Software (NCS-1)
EE1-1.8-related: using additional models for higher temporal layers
EE1-1.8-related: encoder-only optimization for NN based in-loop filter with a single model
EE1-1.8: More refinements on NN based in-loop filter with a single model
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Low latency and constrained complexity (AHG7)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
EE1-2.3：A CNN-based Super Resolution Method with GOP Level Adaptive Resolution
AHG11: Deep Reference Frame Generation for Inter Prediction Enhancement
Common Test Conditions and evaluation procedures for neural network-based video coding technology
EE1-related: More refinements on EE1-1.4 and EE1-1.5
EE1-1.5: Neural network based in-loop filter with a single model
EE1-1.4: Neural network based in-loop filter with 2 models
AHG11: Neural Network based Super Resolution for Video Coding Using Multiple Side Information
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Low latency and constrained complexity (AHG7)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
EE1-1.1: The Performance of Single-Model Filter Trained on the VTM and ECM Reconstruction
AHG11: Deep Reference Frame Generation for Inter Prediction Enhancement
Common Test Conditions and evaluation procedures for neural network-based video coding technology
AHG10: Report of temporal layer dependent deblocking filter setting for HM
EE1-related: The performance of EE1 Test 1.1 and Test 1.2 on ECM-4.0
EE1-related: Additional results on Test 1.1 and Test 1.2 with 8-bit quantization
EE1-1.2: Neural network based in-loop filter with a single model
EE1-1.1: Neural network based in-loop filter with 2 models
JVET AHG report: Low latency and constrained complexity (AHG7)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
Adaptively bypass affine ME in VTM
Evaluation of objective quality metrics on HEVC, VVC and AV1 contents
Evaluation of 17 objective quality metrics on JVET contents
Quality evaluation of internal 10-bit versus 8-bit processing with 8-bit source content
On low delay configuration
AHG10: Report of Deblocking filter setting for VTM
AHG-7 LLCC Scenarios and baseline configurations
JVET AHG report: Neural network-based video coding (AHG11)
AHG10: Fast skip of TT split partitioning on top of ECM reference software
EE1-1.1-related: alternative filter designs
EE1-1.1-related: the result of neural network based in-loop filter on ECM
EE1: Summary of Exploration Experiments on Neural Network-based Video Coding
EE1-1.1: neural network based in-loop filter with constrained storage and low complexity
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Low latency and constrained complexity (AHG7)
AHG11: NN-based Reference Frame Interpolation for VVC Hierarchical Coding Structure
AHG10: Deblocking filter setting for VTM
Common Test Conditions and evaluation procedures for neural network-based video coding technology
Exploration Experiments on Neural Network-based Video Coding (EE1)
AHG11: NN-based Reference Frame Interpolation for VVC Hierarchical Coding Structure
EE2-related: On propagating intra prediction mode for IBC
AHG2/AHG9: On Multiview View Position (MVP) SEI message
EE1: Summary of Exploration Experiments on Neural Network-based Video Coding
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG11: neural network based in-loop filter with constrained storage and low complexity
AHG11: neural network based in-loop filter with adaptive model selection
AHG8: General Constraints Information (GCI) flags for operation range extensions
EE1-1.5: neural network based in-loop filter using depthwise separable convolution and regular convolution
EE1-1.3: neural network based in-loop filter
AHG2/AHG8: Comments on VVC operation range extensions
Common Test Conditions and evaluation procedures for neural network-based video coding technology
Exploration Experiments on Neural Network-based Video Coding (EE1)
AHG11: neural network based cross-component prediction model
EE2-related: Low complexity sign prediction
AHG9: Independently coded region output SEI message
Subpicture-wise reference picture resampling and scalability for Game/E-sport contents streaming
AHG11: neural network based in-loop filter
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
EE1: neural network based in-loop filter using depthwise separable convolution and regular convolution
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
EE1: SSIM based CNN model for in-loop filtering
AHG9: Multiview view position SEI message
AHG9: Comments on multiview-related SEI messages in VSEI
Common Test Conditions and evaluation procedures for neural network-based video coding technology
Exploration Experiments on Neural Network-based Video Coding (EE1)
EE1-1.1: neural network based in-loop filter using depthwise separable convolution and regular convolution (JVET-U0061)
EE1: Summary of Exploration Experiments on Neural Network-based Video Coding
AHG11: Neural network based temporal processing
AHG9/AHG11: SEI messages for carriage of neural network information for post-filtering
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
Common Test Conditions and evaluation procedures for neural network-based video coding technology
A video dataset for training in neural network based video coding
Performance of a VVC Software Decoder on Mobile Platform
EE-1.1-related: BD-Rate improvements to JVET-T0057 neural network based in-loop filter using depthwise separable convolution and regular convolution
AHG9/AHG11: SEI message for carriage of neural network information for post filtering
EE: SSIM based CNN model for in-loop filtering
EE-1.1: A comparison of depthwise separable convolution and regular convolution with the JVET-T0057 neural network based in-loop filter
EE Summary Report: Neural Network-based Video Coding
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG11: Updated information on inter-prediction coding tool with deep neural network
JVET common test conditions and evaluation procedures for neural network-based video coding technology
JVET AHG report: Tool reporting procedure and testing (AHG13)
Versatile Video Coding Editorial Refinements on Draft 10
Methodology and reporting template for neural network coding tool testing
[DNNVC] AhG on deep neural networks based video coding
Performance of a VVC software decoder
JVET AHG report: Neural-network-based video coding (AHG11)
AHG11: A case study to reduce computation of a neural network based in-loop filter by pruning
AHG11: Information on inter-prediction coding tool with deep neural network
AHG2: Editorial and errata input on VVC draft text
AHG11: SSIM based CNN model for in-loop filtering
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
Report of AHG11 Meeting on Neural Network-based Video Coding on 2020-07-30
Versatile Video Coding (Draft 10)
AhG on neural network based coding tools
Performance Comparison of Screen Content Coding between HEVC and VVC
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Tool reporting procedure and testing (AHG13)
JVET AHG report: Screen content coding (AHG11)
AHG9: On decoding process for symmetric motion vector difference reference indices
Versatile Video Coding (Draft 9)
On chroma QP mapping
AHG9/AHG8/AHG12: On subpicture bitstream extraction process
On Signaling of TU Luma Coded Flag for CU with ACT
AHG8/AHG9/AHG12: On reference picture resampling with scalability
AHG9: Bugfix and Cleanup on ph_no_output_of_prior_pics_flag and ph_gdr_or_irap_pic_flag
AHG9: On reference picture list with generating unavailable reference picture
AHG9: On gradual decoding refresh
AHG9: cleanup on parameter sets and GCI
AHG8/AHG9: On signaling reference picture resampling
AHG9: On field coding
AHG9: On signaling IRAP and GDR pictures
AHG9: Clean-ups on general constraint flags
JVET AHG report: Tool reporting procedure and testing (AHG13)
CCLM: common text for spec bugfixes
CU level transform size restriction for adaptive color transform
Fix on minimum QT size value range
Simplification on CCLM
JVET AHG report: Screen content coding (AHG11)
AHG 9: Combination of JVET-R0177/R0301 and JVET-R0074/R0232 on APS Signaling and Semantics Cleanup
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG9/AHG12: On signalling of subpicture and slice in SPS
Implicit binary split at picture boundary
AHG12: On signalling of chroma QP
AHG9: Clean-ups on picture header
AHG9/AHG12: On signalling of subpicture and slice in PPS
AHG9: On derivation of picture output flag
AHG9/AHG12: On mixed NAL unit types
AHG15: On Chroma Quantization Matrix Signalling
AHG9/AHG12: On signalling of subpicture ID
AHG12: on scaling_list_chroma_present_flag in APS
AHG8/AHG9: On signalling max number of sublayers
AHG9: On picture output for non-reference pictures
AHG9/AHG12: Virtual boundary signalling with subpictures
AHG8/AHG9: On derivation of sublayer number in output layer set
Versatile Video Coding (Draft 8)
SPS level control over the number of merge candidates
Integrated Text for GEO
AHG15: Improvement for Quantization Matrix Signaling
CC-ALF: Integrated Text for the Cross Component Adaptive Loop Filter
Interaction between ACT and BDPCM chroma
Interaction between ACT and cross-component coding tools
On chroma QT split
AHG9: Text for combination of wrap around offset and RPR
AHG15: Clean up for signaling quantization matrix
On minimum chroma QT size derivation
AHG 9: On conditioning the presence of inter-/intra- related syntax elements in PH
AHG 9: Picture header syntax cleanups
AHG9: Picture Header in Slice Header
AHG11: picture/slice level deblocking control flag for IBC
Constraint on minimum CU size
AHG8/AHG9: On video parameter set ID
CE3-related: Computation reduction in the derivation of Rice parameter for abs_remainder[ ] in regular residual coding
CE5-related: Simplified CCALF
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Tool reporting procedure and testing (AHG13)
JVET AHG report: Screen content coding (AHG11)
CE4-Related: On-the-fly Weighting Index to Sample Blending Weight Conversion without Table Look-Up on Top of Combined Test in Q0061
AHG 9: On picture header
CE3-related: Modified TS residual coding
AHG9: On temporal sub-layer switching
AHG8/AHG9/AHG12: On subbitstream extraction
AHG9/AHG12: On adaptation parameter set identification
AHG9/AHG12: On mixed NAL unit type support
AHG9/AHG12: Independently coded regions output window SEI message
CE4-Related: On-the-fly Weighting Calculation and MV Storage Derivation in GEO
CE4-Related: Look-Up Table Free Weighting Index to Sample Blending Weight Calculation By Using Piecewise Constant Function in GEO
AHG9: On wrap-around motion compensation
CE4 related: cleanup for signaling maximum number of triangle merge candidates
AHG12: Signaling of chroma presence in PPS and APS
CE4-Related: On-the-fly Weighting Index to Sample Blending Weight Conversion without Table Look-Up in GEO
AHG9: On contant picture output
Conditional signaling of SAO
CE3-related: Bit-exact simplification of Rice parameter selection for regular residual coding
Modifications to VVC Draft 7 to support monochrome and independently coded color planes
AHG8/AHG9: On alignment across layers
AHG9/AHG8: On random access related flags
AHG8/AHG9: Layer dependency constraints for parameter set reference
CE1-4: Disable deblocking for affine sub-PU edges when PROF is applied
CE5-2.2: Multiplication removal for CCALF with coefficient range in [-8, 8]
Versatile Video Coding (Draft 7)
Non-CE8: An alternative IBC virtual buffer setting to avoid reference sample wrapping around
Proposed text for MTS related HLS (harmonization of JVET-P0495, JVET-P0501 and JVET-P0569)
Non-CE8: Constraints on IBC reference block locations
Non-CE5: Combination of JVET-P0470 and JVET-P0557 on simplification of CC-ALF
AHG8: Signalling of output layer sets
Non-CE5: On non-linear ALF clipping values
AHG8: On output layer set and PTL signaling
AHG8/AHG12: Efficient signaling of picture size and partitioning information
AHG17: On max QT/BT/TT size signaling
AHG16: Bugfix for local dual tree
Non-CE8: On IBC merge list size signaling
Non-CE8: IBC chroma mode with dual-tree
Non-CE8: IBC slice level on/off
Non-CE4: On DMVR without padding
Non-CE4: On DMVR early termination
Non-CE3: ISP extension to avoid small Chroma intra blocks
CE7-related: Combination of JVET-P0435, JVET-P0437, and JVET-P0447 for residual coding at 1.75 bins/coefficient
CE7-related: Rice parameter range extension in residual coding with transform skip
CE7-related: Modifications to transform skip coefficient sign flag coding
AHG8: On signaling interlayer reference picture list
CE3-related: Simplification for MIP matrix multiplication
JVET AHG report: Tool reporting procedure (AHG13)
CE6-2.2a/c: LFNST with unified kernels
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
JVET AHG report: Screen content coding (AHG11)
Non-CE5: Simplification of Cross Component Adaptive Loop Filter
JVET AHG report: Neural Networks in Video Coding (AHG9)
AHG8/AHG12: Output layer set with subpictures
AhG16: On dynamic internal bit depth
Non-CE4: Unified AMVR signaling
Non-CE4: On inheritance of alternative half-pel interpolation filter flag in MMVD
AHG12: On padding processing with subpictures
Non-CE4: Motion pruning with alternative half-pel interpolation filter flag
AHG12: Subpicture-level conformance window
AHG8/AHG12: Signaling subpicture identifier
AHG17: Parameters in AUD
Non-CE5: On deblocking on affine internal prediction sub-block edges
Non-CE3: ISP simplifications
CE7-related: unification for joint chroma residue coding modes
Non-CE4: Encoder optimization for subblock-based merge candidate search
AHG17: On signaling CTU size in SPS
Non-CE3/AHG8: On picture size restriction
AHG18: Interaction between lossless coding and max transform size
Non-CE6: Cleanup on MTS related HLS
CE7-related: Modifications to transform skip significant flag coding
AHG8: On signaling output layers
AHG8/AHG17: On signaling reference picture resampling
CE6 related: Harmonization of CE6-1.1 and two-mode LFNST
CE6-2.2d: Combination of CE6-2.2a and CE6-2.3
Versatile Video Coding (Draft 6)
Bitstream conformance with a virtual IBC buffer concept
CE10: Summary Report on Neural Network based Filter for Video Coding
CE7-related: Unification of Rice parameter tables in residual coding
Non-CE4: Redundancy removal for merge mode signaling
CE6-related: Unified LFNST using block size independent kernel
Non-CE: Weighted intra and inter prediction mode
CE7-related: Context reduction of transform coefficient significance flag
Non-CE8: On signaling of IBC block vector predictor list size
CE8-related: Modulo operations for IBC block vectors
Non-CE6: Configurable maximum transform size in VVC
JVET AHG report: Screen Content Coding (AHG11)
Non-CE3: Unification of PDPC for diagonal intra prediction modes
JVET AHG report: Tool reporting procedure (AHG13)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG12: On signaling for slice, tile and brick
JVET AHG report: Neural Networks in Video Coding (AHG9)
Versatile Video Coding (Draft 5)
CE4-2.4: Simplifications of interweaved affine mode
Non-CE4: Adaptive subblock size for affine motion compensation
AHG11: SCC test sequences for VVC standardization and suggestion for class F update
Non-CE4: On prediction refinement with optical flow
AHG8/AHG17: Layered Random Access point (LRA)
AHG8: E-Sport Use cases of VVC region-wise scalability and its system support
CE7: Modified limitation on context coded bins for residual coding of Transform Skip mode (CE7-3.5 and CE7-3.6)
AHG8: Region-wise scalability support with reference picture resampling
AHG8/AHG12: On sub-picture partitioning support with layers
AHG8: On spatial scalability support with reference picture resampling
Non-CE4: Context reduction for merge mode
Non-CE3/6: Transform selection for MRL
Non-CE6: Harmonization of LFNST, MIP and implicit MTS
AHG17: On virtual bounary signaling
AHG8: Signaling and filtering for Reference Picture Resampling (RPR)
Non-CE8: Modified intra mode associated with BDPCM
Non-CE6: Modified high-level syntax control on implicit transform
CE3-related: Redundant bit saving for CE3-2.2
Non-CE4: On LIC for Affine
CE10: Dense Residual Convolutional Neural Network based In-Loop Filter (Tests 2.5 and 2.7)
CE8-1.7: Single HMVP table for all CUs inside the shared merge list region for IBC
Non-CE3: Simplifications for MIP
CE9-2.3: CIIP with disabled BDOF
AHG8: Spatial Scalability using Reference Picture Resampling
AHG17: Signalling zero or more Sub-Profiles
Description of Core Experiment 10 (CE10): Neural Network based Filter for Video Coding
Support of 4:4:4 and 4:2:2 chroma formats in VVC
CE8: Combination of MMVD and IBC mode (Test CE8-1.3a and CE8-1.3b)
Non-CE6: Joint proposal on configurable max transform size of JVET-N0362 and JVET-N0227
AHG10: Enable Rate Control with In-Loop Reshaping
CE10-related: Simplification and Improvement of combined intra-inter prediction mode
AHG12: On tile group design
CE8-related: Combination test of JVET-N0176/JVET-N0317/JVET-N0382 on simplification of IBC vector prediction
CE6-related: Modified encoder decision for transform skip
AHG17: On decoded picture buffer management
Non-CE6: Further cost reduction for primary transform
AOV YUV4:4:4 sequence for VVC standardization and suggestions for class F
CE4-related: Signaling of maximum number of triangle candidates
CE8-related: Modified limitation on context coded bins for CE8-4.3a and CE8-5.1a
CE4-related: modification of HMVP update process inside the shared merging candidate list region
Non-CE8: IBC search range increase for small CTU sizes
AHG16/Non-CE8: IBC search range adjustment for implementation consideration
CE8-related: unified IBC block vector prediction
Non-CE2: Combination of affine MV clip and prediction refinement with optical flow
CE13: Summary Report on Neural Network based Filter for Video Coding
CE8: BDPCM with harmonized residual coding and CCB limitation (CE8-3.1a, CE8-3.1b, CE8-5.1a, CE8-5.1b)
CE3-related: Unified MPM list based on CE3-3.3 and CE3-3.5.1
CE3-3.3: MPM list harmonization
AHG12: On sub-picture design
CE4-related: Fix of MMVD signalling
CE13: Dense Residual Convolutional Neural Network based In-Loop Filter (CE13-2.2 and CE13-2.3)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
CE6-related: MPM based non-separable secondary transform
CE3-related: Harmonization between ISP and WAIP
JVET AHG report: Tool reporting procedure (AHG13)
CE7-2: Reduced number of context-coded bins
JVET AHG report: Screen Content Coding (AHG11)
JVET AHG report: Neural Networks in Video Coding (AHG9)
CE2-4.10: Constraint on constructed affine MV range
Non-CE6: Configurable max transform size in VVC
Versatile Video Coding (Draft 4)
CE2-related: Simplifications of interweaved affine mode
CE2-5.1: Affine HMVP with modified affine inheritance
AHG12: On tile design
An implementation of adaptive color transform in VVC
Support of chroma 4:4:4 format in VVC
CE2-4.4: Affine block memory bandwidth reduction by MV clip
AHG16: Memory bandwidth reduction for small CUs
CE2-2.2: Affine merge with prediction offset
[AHG19] On Signaling of Adaptive Resolution Change
CE6-1: Unification between MTS and Transform Skip mode
AHG17: On NAL Unit header design for VVC
AHG17: On Forbidden-Zero Bit in NAL Unit Header
Description of Core Experiment 13 (CE13): Neural Network based Filter for Video Coding
Methodology and reporting template for neural network coding tool testing
CE8: CPR reference memory reuse with reduced memory requirement (CE8.1.2b and CE8.1.2c)
CE8: CPR reference memory reuse without increasing memory requirement (CE8.1.2a and CE8.1.2d)
BoG report on neural networks for video coding
AHG9: Complexity analysis about neural network video coding tools
CE10-related: LIC inheritance restrictions and interaction with GBI
CE10-related: Using regular merge index signaling for triangle mode
AHG9: Test Results of Dense Residual Convolutional Neural Network based In-Loop Filter
Non-CE8: Combination of Multi Hypothesis Intra and CPR mode
Non-CE8: Combination of MMVD and CPR mode
CE1: Rectangular virtual pipeline data unit (test 1.1.1) and supplementary results
AHG10: Quality dependency factor based rate control for VVC
CE4-related: MMVD offset table signaling
CE2-related: Constraint on constructed affine merge candidates
AHG8: On wrap around motion compensation
CE10-related: Simplified multi-hypothesis intra-inter mode
CE2: Affine merge with prediction offset (Test CE2.2.4)
Non-CE8: CPR with chroma 4x4 sub-block size when dual-tree is on
Non-CE8: Inter mode related flag signaling when current picture is the only reference picture
Non-CE8: CPR flag signaling at slice level
Non-CE8: Mismatch between text specification and reference software on ATMVP candidate derivation when CPR is enabled
CE2-related: Adaptive sub-block MV clip for affine blocks
CE3-related: Simplified look-up table for CCLM mode
CE3-related: Modifications on MPM list generation
CE2-related: Combination of CE2.2.3.d and affine inheritance from motion data line buffer
CE4-related: Improved context for prediction mode flag
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
CE4: Summary report on inter prediction and motion vector coding
AHG17: On decoded picture buffer management for VVC
CE7-related: Reduced maximum number of context-coded bins for transform coefficient coding
Versatile Video Coding (Draft 3)
JVET AHG report: Tool reporting procedure (AHG13)
CE8: Palette predictor list enhancement (Test 8.2.6)
CE8: palette mode when dual-tree is enabled (Test 8.2.4)
CE8: Palette index map scan order constraints (Test 8.2.3)
CE2: Sub-block MV clip in planar motion vector prediction (test 2.3.2)
Description of Core Experiment 4 (CE4): Inter prediction and motion vector coding
JVET AHG report: Neural Networks in Video Coding (AHG9)
JVET AHG report: Screen Content Coding (AHG11)
AhG-13: On Merge List Size
CE6: Compound Orthonormal Transform (Test 6.1.1 a/b/c/d)
CE6 related: Unification of Transform Skip mode and MTS
CE6: MTS up to 16-length (Test 6.3.8)
AHG17: On picture order count for VVC
AHG17: On component type indication for VVC
AHG12: On tile group identification for VVC
CE6: RQT-like transform sub-block splitting (Test 6.4.3
CE2/4-related: Unified merge list size for block and sub-block merge modes
CE4-related: Simplified merge candidate list for small blocks
AHG17: On leading picture for VVC
AHG17: On random access point for VVC
AHG17: On NAL unit header design for VVC
CE3: Intra mode coding (Test 3.2)
CE4: History based spatial-temporal MV prediction (Test 4.2.4)
CE6: Fast DST-7/DCT-8 with dual implementation support (Test 6.2.3)
CE2-related: Simplified context model for triangular prediction mode
CE8-related: BDPCM entropy coding with reduced number of context coded bins
CE4-related: Triangle merge index signaling
CE9: Constrained intra prediction with DMVR (test 9.2.4)
CE2: History Based Affine Motion Candidate (Test 2.2.3)
CE4-related: Constraint on GBi index inheritance in Merge Mode
AHG17: Proposed NAL Unit Header Design Principles
CE4-related: Simplified MVD coding
Methodology and reporting template for neural network coding tool testing
AHG9: Dense Residual Convolutional Neural Network based In-Loop Filter
BoG report on Neural Networks for Video Coding
JVET AHG report: Tool reporting procedure (AHG13)
CE8: CPR mode with local search ranges (Test CE8.3.1 and CE8.3.2)
CE4-related: affine merge mode with prediction offsets
CE6-related: Unification of Transform Skip mode and MTS
CE3-related: Unification of angular intra prediction for square and non-square blocks
CE3-related: Intra mode coding
CE7-related: Reduced context models for transform coefficients coding
JVET AHG report: Screen Content Coding (AHG11)
CE4-related: constrained model-based affine merge
CE4-related: Sub-block MV clipping in planar motion vector prediction
CE4-related: Sub-block MV clipping in affine prediction
CE6: Fast DST-7/DCT-8 with dual implementation support (Test 6.1.4)
CE15-related: Palette predictor list enhancement
CE15-related: Palette index map scan order constraints
CE15-related: Palette mode when dual-tree is enabled
CE4: Summary report on inter prediction and motion vector coding
CE1-related: Non-square virtual pipeline data unit
CE4-related: History Based Affine Merge Candidate
CE3: Multiple reference line intra prediction (Test 1.1.1, 1.1.2, 1.1.3 and 1.1.4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
AHG10: Adaptive lambda ratio estimation for rate control in VVC
CE6: Compound Orthonormal Transform (Test 6.1.7 f/g)
CE6: Coupled primary and secondary transform (Test 6.3.2)
Versatile Video Coding (Draft 2)
JVET AHG report: Neural Networks in Video Coding (AHG9)
CE6: On 8-bit primary transform core (Test 6.1.3)
Fix of Initial QP Signaling
CE4: Combined test of CE4.4.2 and CE4.4.7
CE8: CPR mode with non local search ranges (Test CE8.3.3, CE8.3.4, CE8.3.5 and CE8.3.6 )
CE8: CPR mode with dual-tree support (Test CE8.2)
Description of Core Experiment 4 (CE4): Inter prediction and motion vector coding
Methodology and reporting template for tool testing
CE4-related: History based spatial-temporal MV prediction
CE8-related: CPR mode with merge mode improvements
CE8-related: CPR mode with local search range optimization
CE9-related: Constrained intra prediction with decoder side motion vector derivation
CE4.4.2: Long distance merge candidates
CE4: ranking based spatial merge candidate list for inter prediction (Test CE4.4.14)
CE4: Extension of merge and AMVP candidates for inter prediction (Test CE4.4.10)
CE3: Simplifications for chroma intra coding (Test 2.3.1 and 2.3.2)
CE9.2.14: Interpolation filters in DMVR
CE9.1.7: Constrained decoder side motion vector derivation
CE1-1.3.1: Partial CU for picture boundary handling
CE4: Additional merge candidates (Test 4.2.13)
CE3-related: Wide-angle intra prediction for non-square blocks
CE4-related: Encoder optimization on top of CE 4.2.13
CE3-related: Combination of CE3-5.1.1, 5.4.4 and 5.5.2
Crosscheck of JVET-K0411: AHG11: Palette mode
CE3-related: Wide angular intra prediction for non-square blocks
CE4-related: Reduce line buffer for additional merge candidates
AHG9: Dense Residual Convolutional Neural Network based In-Loop Filter
Rate Control for VVC
CE2-related: Improvement on the implementation of adaptive loop filter
CE9-related: Constrained Decoder Side Motion Vector Derivation
CE3-related: MPM based multi-line intra prediction scheme
CE6-related: Compound orthonormal transform
CE6-related: Fast DST-7/DCT-8 with dual implementation support
CE6-related: On 8-bit primary transform core
Tencent test sequences, and Class F test set restructure
CE4-related: ranking based spatial merge candidate list for inter prediction
CE8-2.1: Current picture referencing using block level flag signaling
CE8-2.2: Current picture referencing using reference index signaling
CE4: Summary report on inter prediction and motion vector coding
CE1-related: Partial CU for picture boundary
CE9-related: Memory bandwidth reduction for DMVR
CE4-related: extension of merge and AMVP candidates for inter prediction
CE3-related: Simplifications for chroma intra coding
JVET AHG report: Neural Networks in Video Coding (AHG9)
JVET AHG report: Screen Content Coding (AHG11)
CE6: Coupled primary and secondary transform (Test 3.1.1 and Test 3.1.2)
CE6: Matrix multiplication based NSST (Test 2.4.1 and Test 2.4.2)
CE6: Block size dependent zero-out transform (Test 1.14)
CE3: Mode dependent reference line selection (Test 5.1.1 and 5.1.2)
Description of Core Experiment 4 (CE4): Inter prediction and motion vector coding
JVET AHG report: Test material (AHG4)
AHG9: Crosscheck of CNN filter in JVET-I0022 as in-loop filter and post-processing filter
Tencent test sequences for video coding development
Coupled primary and secondary transform
Merge mode modification on top of Tencent’s software in response to CfP
Intra block copy improvement on top of Tencent’s CfP response
Adaptive chroma QP offset on top of Tencent's CfP response
Further work on top of Tencent’s CfP response
Coding performance of Tencent’s structure-only scheme
Non-Square CTU on top of JVET-J0021
Description of SDR video coding technology proposal by Tencent
Further investigations on multi-line intra prediction
JVET AHG report: Neural Networks in Video Coding (AHG9)
Cross-check of JVET-D0044 Parallel deblocking filter for QTBT
Crosscheck report of JVET-D0135
Cross-check of JVET-D0025 Encoder Bug Fixes of Quantization in QTBT
Crosscheck report of JVET-D0134
Cross-check of JVET-D0111 Multiple Direct Modes for chroma intra coding
AHG5: Speed-up for JEM-3.1
AHG10: Fast skip of TT split partitioning on top of VTM-14.0 and ECM reference software
CE2.3.2: Sub-block MV clip in planar motion vector prediction
Cross-check of JVET-B0038: Harmonization of AFFINE, OBMC and DBF [Never delivered]
AHG9: Rotation representation extensions of Gaussian Splatting Information SEI message
AHG9: Processing History Information SEI
AHG9: Historical Information SEI message
AHG9: On PSI SEI message
AHG9: On video full range indication
AHG9: On Danmu Information SEI message
AHG9: On Quality Metric SEI message
AHG9: Editorial improvements for TuC
JVET AHG report: Neural network-based video coding (AHG11)
JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8)
JVET AHG report: Test material and visual assessment (AHG4)
JVET AHG report: Draft text and test model algorithm description editing (AHG2)
Common test conditions and evaluation procedures for neural network-based video coding technology
AHG12: SbTMVP with MMVD