Research map / Video / Video segmentation and tracking
High Resolution Neural Video Coding with Bi-directional Confidence-Guided Reference Information Modeling
Feng Ye, Kai Zhang, Li Zhang, Chuanmin Jia
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Hierarchical Motion Representation (ablation) | HR-NVC baseline · Overall average (ablation) | BD-rate (PSNR): -3.57 | Improved |
| add Contextual Asymmetric Harmonization (confidence-guided fusion) (ablation) | HR-NVC · Overall average (ablation) | BD-rate (PSNR): -3.57 -> -9.57 | Improved |
| combine HMR with CAH (ablation) | HR-NVC · Overall average (ablation) | BD-rate (PSNR): -9.57 -> -13.68 | Improved |
| add Spatial Anchor (low-resolution flow prior) (ablation) | HR-NVC · Overall average (ablation) | BD-rate (PSNR): -13.68 -> -15.13 | Improved |
| add Spatial Anchor (ablation) | HR-NVC · UVG (ablation) | BD-rate (PSNR): -7.23 -> -12.51 | Improved |
| add Temporal Virtual Anchor (ablation) | HR-NVC · Overall average (ablation) | BD-rate (PSNR): -15.13 -> -15.77 | Improved |
| add Temporal Virtual Anchor (ablation) | HR-NVC · JCT-VC Class C and D (ablation) | BD-rate (PSNR): -19.71 -> -19.71 | No clear effect |
| enable Temporal Virtual Anchor at 1080P (ablation) | HR-NVC · 1080P complexity | Dec. time: 743ms -> 755ms | Hurt |
| use confidence-guided bi-directional B-frame coding vs DCVC-B | HR-NVC · JVET 4K average | BD-rate (PSNR): -27.53 -> -31.84 | Improved |
Closest papers by meaning
- Neural B-frame Video Compression with Bi-directional Reference Harmonization (NeurIPS 2025 · similarity 0.93)
- Neural Video Compression with Context Modulation (CVPR 2025 · similarity 0.89)
- Towards Practical Real-Time Neural Video Compression (CVPR 2025 · similarity 0.87)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.87)
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.87)
- Augmented Deep Contexts for Spatially Embedded Video Coding (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
