Research map / Video / Video segmentation and tracking
Learned Video Compression
Oren Rippel, Sanjay Nair, Carissa Lew, Steve Branson, Alexander G. Anderson, Lubomir Bourdev
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 |
|---|---|---|---|
| use learned video codec instead of H.265 on SD video | HEVC/H.265 · CDVL SD | bitrate at equal MS-SSIM: up to 60% larger | Improved |
| use learned video codec instead of H.264 on HD video | AVC/H.264 · Xiph HD 1080p | bitrate at equal MS-SSIM: up to 35% larger | Improved |
| use learned video codec instead of H.265 and VP9 on HD video | H.265, VP9 · Xiph HD 1080p | bitrate at equal MS-SSIM: up to 20% larger | Improved |
Closest papers by meaning
- Learning End-to-End Lossy Image Compression: A Benchmark (TPAMI 2021 · similarity 0.92)
- ELF-VC: Efficient Learned Flexible-Rate Video Coding (ICCV 2021 · similarity 0.91)
- AlphaVC: High-Performance and Efficient Learned Video Compression (ECCV 2022 · similarity 0.90)
- M-LVC: Multiple Frames Prediction for Learned Video Compression (CVPR 2020 · similarity 0.89)
- MoVie: Multimodal Video Compression with Text Guidance (ICML 2026 · similarity 0.89)
- Towards Practical Real-Time Neural Video Compression (CVPR 2025 · similarity 0.88)
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.
