Back to Search
Author profile
Affiliations
Documents
EE1-3.1: Very Small Deep Reference Frame Generation Network for Inter Prediction Enhancement
AHG11: Improved H-DRF with Weighted Fusion and Optimized YUV Processing
AhG14: SIMD Improvements of Operators in SADL Library
EE1-4.1: Deep Reference Frame Generation for Inter Prediction Enhancement with Structural Re-parameterization
AHG11: Very Small Deep Reference Frame Generation Network for Inter Prediction Enhancement
AHG4/AHG17: AIGC test sequences
AHG11: Efficient Depthwise Separable Backbone Network for Neural Network in-Loop Filter
[AHG17] Wuhan University’s Response in Joint Call for Evidence on Video Compression with Capability beyond VVC
EE1-related: FlowWarp Operator for DRF Integer Inference Optimization
EE1-3.5: Retrained DRF in NNVC-14.0
AHG14: Operator Improvements in the SADL library
EE1-3.1: Deep Reference Frame Generation for Inter Prediction Enhancement with Structural Re-parameterization
AHG11: Deep Reference Frame Generation for Inter Prediction Enhancement with Structural Re-parameterization
EE1-3.2: Deep Reference Frame Generation for Inter Prediction Enhancement
EE1-related: Deep Reference Frame Generation for Inter Prediction Enhancement
EE1-3.1: Deep Reference Frame Generation for Inter Prediction Enhancement
EE1-3.1: Deep Reference Frame Generation for Inter Prediction Enhancement
EE1-2.1: Deep Reference Frame Generation for Inter Prediction Enhancement
Crosscheck of JVET-O0214(Non-CE6: Harmonization of implicit MTS and LFNST)
Non-CE9: BDOF simplifications
Non-CE4: On Merge data signaling
Non-CE4: On MMVD candidate flag coding
Non-CE4: MMVD simplification
CE4: Extension on MMVD (Test 4.2.5)
Crosscheck of JVET-M0331 (CE10-related:A simplification of inter prediction information derivation for Multi-intra-inter mode scheme)
Cross-check of JVET-M0265 (AHG16: Clean-up on MV Rounding)
Crosscheck of JVET-M0068 (Non-CE4: MMVD scaling fix)
Crosscheck of JVET-M0148 (Non-CE9: Simplifications to DMVR search pattern and interpolation for refinement)
CE2: Planar Motion Vector Prediction (test 2.3.1)
CE9: DMVR Simplifications (Test 9.2.3)
CE 4: Merge Offset Extension (Test 4.4.8)
Cross-check of JVET-L0098
CE4.4.11: Combined Average Merge Candidates
CE 9: Refined MVs Partial Usage for Spatial (Test 9.1.5)
CE 9: DMVR Simplifications (Test 9.2.8)
CE 4: Extended Non-adjacent Spatial Merge Candidates (Test 4.4.3)
Cross-check of JVET-K0161 (Spatial-temporal merge mode (non subblock STMVP))
Cross-check of JVET-K0352 (CE4-related: Encoder optimization on top of CE 4.2.13)
CE4: Enhanced Merge Mode(Test 4.2.15)
CE9.4.3:Template Matching based Adaptive Merge Candidate Reorder
CE9: DMVR extension based on template matching(Test 9.3.6)
CE9: Simplification of DMVR(Test 9.1.1)
SW for technology proposal by Samsung, Huawei, GoPro, and HiSilicon – mobile application scenario (JVET-J0024)
Enhanced Merge Mode based on JEM7.0
DMVR Extension Based on Template Matching
Description of SDR, HDR and 360° video coding technology proposal by Huawei, GoPro, HiSilicon, and Samsung – general application scenario
Description of SDR, HDR and 360° video coding technology proposal by Samsung, Huawei, GoPro, and HiSilicon – mobile application scenario
EE3: Enhanced FRUC Template Matching Mode
Cross-check of AHG5: Improved fast encoding setting(TestA)
Enhanced Template Matching in FRUC Mode
EE3: Decoder-Side Motion Vector Refinement Based on Bilateral Template Matching
Cross-check of JVET-D0064 (Table 3)
Cross-check of testA and testB in JVET-D0095 on fast QTBT encoding configuration
Decoder-Side Motion Vector Refinement Based on Bilateral Template Matching
Crosscheck of JVET-AQ0049 (EE1-2.3: Deep Reference Frame Generation for Inter Prediction Enhancement with motion compensation)
EE1-2.4: Combination of test 2.3 (Deep Reference Frame Generation with motion compensation) and tests 2.1 and 2.2
EE1-2.2: Improved H-DRF with Weighted Fusion and Optimized YUV Processing
EE1-2.1: Very Small Deep Reference Frame Generation Network for Inter Prediction Enhancement
AHG11: Efficient Depthwise Separable Backbone Network for Neural Network In-Loop Filter
EE1-related: Deep Reference Frame Generation for Inter Prediction Enhancement