Research map / Image generation / Image restoration
Controllable Generative Reference for Stereo Image Compression via Reliability-Aware Gating
Zhineng Zhao, Mingyao Hong, Fengfan Shi, Zhihai He
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 generative reference from frozen diffusion model (ablation) | stereo compression framework · InStereo2K | BD-PSNR: -1.31 dB without it | Improved |
| add generative reference from frozen diffusion model (ablation) | stereo compression framework · Cityscapes | BD-PSNR: -1.23 dB without it | Improved |
| add ultra-compact semantic control (ablation) | generative reference · InStereo2K | BD-PSNR: -0.76 dB without it | Improved |
| add ultra-compact semantic control (ablation) | generative reference · Cityscapes | BD-PSNR: -0.83 dB without it | Improved |
| add reliability-aware gate (ablation) | entropy model · InStereo2K | BD-PSNR: -1.07 dB without it | Improved |
| add reliability-aware gate (ablation) | entropy model · Cityscapes | BD-PSNR: -0.91 dB without it | Improved |
| use generative-reference method instead of BiSIC | stereo compression · InStereo2K PSNR BDBR | BDBR vs BPG: -48.08% -> -67.64% | Improved |
| use generative-reference method instead of CAMSIC | stereo compression · Cityscapes MS-SSIM BDBR | BDBR vs BPG: -69.67% -> -74.53% | Improved |
| add generative reference synthesis time | stereo compression · InStereo2K runtime | time per image pair (s): 1.29 -> 1.60 | Mixed |
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.
- CAMSIC — CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression (AAAI 2025) · better on 4 of 5 shared results
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
- 3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors (ICML 2025 · similarity 0.86)
- CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression (AAAI 2025 · similarity 0.86)
- GenRec: Knowing Where to Reconstruct and Where to Generate (NeurIPS 2026 · similarity 0.86)
- ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS (NeurIPS 2025 · similarity 0.85)
- CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression (ICLR 2025 · similarity 0.85)
- Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion (ICML 2025 · similarity 0.85)
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.
