Research map / Image generation / Autoregressive and latent generation
Autoregressive-based Progressive Coding for Ultra-Low Bitrate Image Compression
Ziyuan Zhang, Yichong Xia, Bin Chen, Tianwei Zhang, Hao Wang, Han Qiu
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 lossless re-encoding with VAR probabilities (ablation) | ARPC · DIV2K | bitrate: approximately 30% bitrate reduction | Improved |
| add lossless re-encoding (ablation) | ARPC · CLIC2020 | encoding time (s): 0.20 -> 1.8~6.2 | Hurt |
| add scale random dropout (ablation) | ARPC · DIV2K | perceptual metrics | Improved |
| add group mask to bitwise quantizer (ablation) | ARPC · DIV2K | bitrate | Improved |
| use group sizes (4,5,4) rather than (5,6,2) (ablation) | ARPC · DIV2K | BD-rate FID: 64.19 -> 0 | Improved |
| use group sizes (4,5,4) rather than (2,2,9) (ablation) | ARPC · DIV2K | BD-rate FID: 29.87 -> 0 | Improved |
| use modified VAR tokenizer instead of vanilla VAR (ablation) | ARPC · DIV2K | BD-rate FID: 79.51 -> 0 | Improved |
| add GM-BMSRQ to tokenizer (ablation) | tokenizer · ImageNet 512 val | PSNR: 22.6 -> 22.12 | Hurt |
| add scale random dropout to tokenizer (ablation) | tokenizer · ImageNet 512 val | rFID: 0.56 -> 0.67 | Hurt |
| use BLIP-2 instead of lightweight BLIP captioner (ablation) | ARPC · DIV2K | BD-rate FID: 0.08 -> 0 | No clear effect |
| add lossless re-encoding (vs BLIP w/o LRE) (ablation) | ARPC · DIV2K | BD-rate FID: 25.56 -> 0.08 | Improved |
| use InternVL 2.0 detailed captions instead of BLIP2 (ablation) | ARPC · DIV2K | CLIP Score | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- StableCodec — StableCodec: Taming One-Step Diffusion for Extreme Image Compression (ICCV 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion (ICML 2025 · similarity 0.90)
- Towards image compression with perfect realism at ultra-low bitrates (ICLR 2024 · similarity 0.90)
- Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression (CVPR 2025 · similarity 0.88)
- Generative Latent Coding for Ultra-Low Bitrate Image Compression (CVPR 2024 · similarity 0.88)
- Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression (CVPR 2025 · similarity 0.88)
- Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy (NeurIPS 2025 · 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.
