Research map / Video / Video generation
ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling
Daowen Li, Ruixiao Dong, Ying Chen, Kai Li, Ding Ding, Li Li
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 the context model for entropy coding (vs uniform probability) (ablation) | ProGVC · Xiph | DISTS BD-rate: 122.4 / -0.0259 -> 0.0 / 0.0000 | Improved |
| add token generation of discarded fine-scale tokens (ablation) | ProGVC · Xiph | LPIPS BD-rate: 280.9 / -0.1273 -> 0.0 / 0.0000 | Improved |
| add token generation of discarded fine-scale tokens (ablation) | ProGVC · Xiph | PSNR BD-rate: 189.9 / -3.8102 -> 0.0 / 0.0000 | Improved |
| use previous-scale attention instead of self-only attention (ablation) | ProGVC · Xiph | DISTS BD-rate: 6.8 / -0.0021 -> 0.0 / 0.0000 | Improved |
| use previous-scale attention instead of self-only attention (ablation) | ProGVC · Xiph | PSNR BD-rate: 10.9 / -0.3482 -> 0.0 / 0.0000 | Improved |
| use previous-scale attention instead of full causal attention (ablation) | ProGVC · Xiph | Dec. T (s): 1.96 -> 1.53 | Improved |
| use previous-scale attention instead of full causal attention (ablation) | ProGVC · Xiph | DISTS BD-rate: -6.5 / 0.0021 -> 0.0 / 0.0000 | No clear effect |
| condition inter scales on largest intra scale instead of none (ablation) | ProGVC · Xiph | DISTS BD-rate: 37.3 / -0.0171 -> 0.0 / 0.0000 | Improved |
| condition on largest intra scale instead of smallest (ablation) | ProGVC · Xiph | DISTS BD-rate: 42.7 / -0.0191 -> 0.0 / 0.0000 | Improved |
| condition on largest intra scale instead of same-resolution scale (ablation) | ProGVC · Xiph | PSNR BD-rate: 14.4 / -0.5131 -> 0.0 / 0.0000 | Improved |
Closest papers by meaning
- Autoregressive-based Progressive Coding for Ultra-Low Bitrate Image Compression (ICLR 2026 · similarity 0.90)
- GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow (NeurIPS 2026 · similarity 0.87)
- PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models (CVPR 2025 · similarity 0.87)
- Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion (ICML 2025 · similarity 0.87)
- Generative Latent Coding for Ultra-Low Bitrate Image Compression (CVPR 2024 · similarity 0.86)
- Towards image compression with perfect realism at ultra-low bitrates (ICLR 2024 · 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.
