Research map / Image generation / Fast diffusion sampling
DiffuVolume: Diffusion Model for Volume based Stereo Matching
Dian Zheng, Xiao-Ming Wu, Zuhao Liu, Jingke Meng, Wei‐Shi Zheng
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 DiffuVolume to PSMNet | PSMNet · Scene Flow | EPE (px): 1.09 -> 0.97 | Improved |
| add DiffuVolume to GwcNet | GwcNet · Scene Flow | EPE (px): 0.77 -> 0.73 | Improved |
| add DiffuVolume to RAFT-Stereo | RAFT · Scene Flow | EPE (px): 0.72 -> 0.59 | Improved |
| add DiffuVolume to ACVNet | ACVNet · Scene Flow | EPE (px): 0.48 -> 0.46 | Improved |
| add iterative diffusion filtering (vs no iteration) (ablation) | DiffuVolume · Scene Flow | EPE (px): 0.54 -> 0.46 | Improved |
| add volume renewal (ablation) | DiffuVolume · Scene Flow | EPE (px): 0.47 -> 0.46 | Improved |
| add dense integration (ablation) | DiffuVolume · Scene Flow | EPE (px): 0.48 -> 0.46 | Improved |
| increase sampling steps from 1 to 5 (ablation) | DiffuVolume · Scene Flow | EPE (px): 0.48 -> 0.46 | Improved |
| increase sampling steps from 5 to 10 (ablation) | DiffuVolume · Scene Flow | EPE (px): 0.46 -> 0.47 | No clear effect |
| weighted step integration 0-0-0-0.2-0.3-0.5 instead of last step only (ablation) | DiffuVolume · Scene Flow | EPE (px): 0.49 -> 0.46 | Improved |
| add volume renewal on outliers at 5 steps (ablation) | DiffuVolume · Scene Flow | outliers (%): 29.86 -> 23.25 | Improved |
| use volume-embedded diffusion instead of DDPM image-denoising | ACVNet · Scene Flow | EPE (px): 0.59 -> 0.46 | Improved |
Closest papers by meaning
- Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching (AAAI 2020 · similarity 0.88)
- Diffusion Model for Dense Matching (ICLR 2024 · similarity 0.87)
- Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion (CVPR 2025 · similarity 0.86)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.86)
- DEFOM-Stereo: Depth Foundation Model Based Stereo Matching (CVPR 2025 · similarity 0.85)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · 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.
