Research map / Video / Video segmentation and tracking
Scale-Space Flow for End-to-End Optimized Video Compression
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use scale-space warping instead of bilinear warping (ablation) | Low-latency learned video compression · UVG and MCL-JCV | rate-distortion performance: a gap of 1dB for bitrates above 0.1bpp | Helped |
| Use scale-space flow and warping | Learned video compression · UVG | BD rate reduction (equal PSNR) vs. DVC [24]: 13.4% | Helped |
| Use scale-space flow and warping | Learned video compression · UVG | rate savings (equal PSNR) vs. [38]: 42.9% | Helped |
| Use scale-space flow and warping | Learned video compression · UVG | rate savings (equal MS-SSIM) vs. [19]: 30.3% | Helped |
| Optimize the model for MS-SSIM rather than MSE | Scale-space flow video compression · MCL-JCV | PSNR | Mixed |
Closest papers by meaning
- Offline and Online Optical Flow Enhancement for Deep Video Compression (AAAI 2024 · similarity 0.88)
- FVC: A New Framework Towards Deep Video Compression in Feature Space (CVPR 2021 · similarity 0.86)
- DVC: An End-To-End Deep Video Compression Framework (CVPR 2019 · similarity 0.86)
- Neural Video Compression with Context Modulation (CVPR 2025 · similarity 0.85)
- FLAVC: Learned Video Compression with Feature Level Attention (CVPR 2025 · similarity 0.85)
- Neural B-frame Video Compression with Bi-directional Reference Harmonization (NeurIPS 2025 · similarity 0.84)
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.