Research map / Video / Video segmentation and tracking
Deep Generative Video Compression
Read the paperCheck 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 the LSTMP-LG generative video codec | Video compression · Sprites | rate-distortion | Helped |
| Use the LSTMP-LG generative video codec | Video compression · BAIR | rate-distortion | Helped |
| Use the LSTMP-LG generative video codec | Video compression · Kinetics600 | rate-distortion | Mixed |
| Add a global latent state to the local-state architecture (ablation) | LSTMP-LG · Sprites | rate-distortion | Helped |
| Add a global latent state to the local-state architecture (ablation) | LSTMP-LG · BAIR | rate-distortion | Helped |
| Add a global latent state to the local-state architecture (ablation) | LSTMP-LG · Kinetics600 | rate-distortion | Helped |
| Use an LSTM prior conditioned on the full latent history instead of a one-frame deep Kalman filter prior (ablation) | LSTMP-LG · Sprites | rate-distortion | Helped |
| Use an LSTM prior conditioned on the full latent history instead of a one-frame deep Kalman filter prior (ablation) | LSTMP-LG · BAIR | rate-distortion | Helped |
| Use an LSTM prior conditioned on the full latent history instead of a one-frame deep Kalman filter prior (ablation) | LSTMP-LG · Kinetics600 | rate-distortion | Helped |
Closest papers by meaning
- High-Quality Joint Image and Video Tokenization with Causal VAE (ICLR 2025 · similarity 0.90)
- Generative Neural Video Compression via Video Diffusion Prior (CVPR 2026 · similarity 0.90)
- Improved Video VAE for Latent Video Diffusion Model (CVPR 2025 · similarity 0.88)
- Generative Latent Coding for Ultra-Low Bitrate Image Compression (CVPR 2024 · similarity 0.87)
- CV-VAE: A Compatible Video VAE for Latent Generative Video Models (NeurIPS 2024 · similarity 0.87)
- Deep Hierarchical Video Compression (AAAI 2024 · 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.