Research map / Image generation / Fast diffusion sampling
Towards Open-World Generation of Stereo Images and Unsupervised Matching
Feng Qiao, Zhexiao Xiong, Eric Xing, Nathan Jacobs
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 random disparity drop (ablation) | GenStereo · KITTI 2015 stereo generation | PSNR: 16.164 -> 20.439 | Improved |
| add random disparity drop (ablation) | GenStereo · KITTI 2015 stereo generation | LPIPS: 0.1740 -> 0.1079 | Improved |
| add random disparity drop (ablation) | GenStereo · Middlebury 2014 stereo generation | PSNR: 23.552 -> 23.699 | Improved |
| train on mixed datasets instead of one synthetic dataset (ablation) | GenStereo · Middlebury 2014 stereo generation | PSNR: 20.037 -> 23.835 | Improved |
| train on mixed datasets instead of one synthetic dataset (ablation) | GenStereo · KITTI 2015 stereo generation | PSNR: 21.085 -> 22.749 | No clear effect |
| add coordinate embedding (ablation) | GenStereo · Middlebury 2014 stereo generation | PSNR: 22.697 -> 23.407 | Improved |
| add warped image condition (ablation) | GenStereo · Middlebury 2014 stereo generation | PSNR: 22.033 -> 23.407 | Improved |
| add pixel-level loss (ablation) | GenStereo · Middlebury 2014 stereo generation | PSNR: 23.407 -> 23.811 | Improved |
| add adaptive fusion (ablation) | GenStereo · Middlebury 2014 stereo generation | PSNR: 23.811 -> 23.835 | Improved |
| add adaptive fusion (ablation) | GenStereo · KITTI 2015 stereo generation | PSNR: 22.716 -> 22.749 | Improved |
| use SD v2.1 instead of SD v1.5 | GenStereo · Middlebury 2014 stereo generation | PSNR: 23.835 -> 25.142 | Improved |
| use GenStereo-generated right images instead of SD-Inpainting for fine-tuning | PSMNet · KITTI 2015 matching | D1-all: 4.490 -> 3.933 | Improved |
Closest papers by meaning
- Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion (CVPR 2025 · similarity 0.89)
- ZeroStereo: Zero-shot Stereo Matching from Single Images (ICCV 2025 · similarity 0.89)
- AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach (IJCV 2022 · similarity 0.88)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.88)
- MonSter: Marry Monodepth to Stereo Unleashes Power (CVPR 2025 · similarity 0.87)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 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.
