Research map / Video / Video segmentation and tracking
FVC: An End-to-End Framework towards Deep Video Compression in Feature Space
Zhihao Hu, Dong Xu, Guo Sheng Lu, Wei Jiang, Wei Wang, Shan Liu
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 non-local attention in multi-frame feature fusion (ablation) | FVC · HEVC Class D | PSNR: nearly 0.2dB | Improved |
| add multi-frame feature fusion module (ablation) | FVC-basic · HEVC Class D | PSNR: 0.5dB at 0.3bpp | Improved |
| add multi-frame feature fusion module (ablation) | FVC-basic · HEVC Class D | BDBR (%): -7.09 -> -18.39 | Improved |
| perform residual compression in feature space instead of pixel space (ablation) | FVC-basic · HEVC Class D | PSNR: 0.3dB at 0.38bpp | Improved |
| perform motion compensation in feature space instead of pixel space (ablation) | FVC-basic · HEVC Class D | PSNR: 1.2dB at 0.4bpp | Improved |
| use deformable compensation instead of optical-flow motion compensation (ablation) | DVC* · HEVC Class C | PSNR: 1.75dB at 0.017bpp | Improved |
| use deformable compensation instead of optical-flow motion compensation (ablation) | DVC* · HEVC Class C (RaceHorses) | PSNR: 0.27dB gain with 65% bpp | Improved |
| replace DVC with feature-space FVC-basic (ablation) | DVC · HEVC Class D | BDBR (%): 14.08 -> -7.09 | Improved |
| add multi-frame feature fusion (cost) (ablation) | FVC-basic · HEVC Class D | coding time (ms): 201ms -> 548ms | Hurt |
Closest papers by meaning
- FVC: A New Framework Towards Deep Video Compression in Feature Space (CVPR 2021 · similarity 0.99)
- DVC: An End-To-End Deep Video Compression Framework (CVPR 2019 · similarity 0.88)
- FLAVC: Learned Video Compression with Feature Level Attention (CVPR 2025 · similarity 0.87)
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.87)
- RivuletMLP: An MLP-based Architecture for Efficient Compressed Video Quality Enhancement (CVPR 2025 · similarity 0.86)
- Augmented Deep Contexts for Spatially Embedded Video Coding (CVPR 2025 · similarity 0.86)
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.
