Research map / Label-efficient and robust learning / Test-time adaptation
PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, Kwanghoon Sohn
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 meta-learning (ML) to training the base network (ablation) | MADNet with full adaptation · KITTI short-term | D1-all: 6.68 -> 3.12 | Improved |
| add PointFixNet point loss without meta-learning (ablation) | MADNet with full adaptation · KITTI short-term | D1-all: 6.68 -> 8.06 | Hurt |
| add PointFixNet on top of meta-learning (ablation) | MADNet with full adaptation · KITTI short-term | D1-all: 3.12 -> 2.00 | Improved |
| add PointFixNet on top of meta-learning (ablation) | MADNet with full adaptation · KITTI short-term | EPE: 0.96 -> 0.74 | Improved |
| train MADNet with PointFix before adaptation | MADNet · KITTI mid-term, no adaptation | D1-all: 38.35 -> 16.94 | Improved |
| train MADNet with PointFix before adaptation | MADNet · KITTI mid-term, no adaptation | EPE: 8.18 -> 2.12 | Improved |
| train MADNet with PointFix, full adaptation | MADNet · KITTI short-term | D1-all: 6.68 -> 2.00 | Improved |
| train MADNet with PointFix, MAD adaptation | MADNet · KITTI short-term | D1-all: 11.82 -> 2.64 | Improved |
| train MADNet with PointFix, MAD adaptation | MADNet · KITTI mid-term | D1-all: 4.15 -> 2.16 | Improved |
| use PointFix with MAD adaptation instead of MADNet with MAD++ adaptation | MADNet · KITTI mid-term | D1-all: 3.56 -> 2.16 | Improved |
| train MADNet with PointFix, no adaptation | MADNet · DrivingStereo weather, short-term | D1-all: 58.12 -> 33.52 | Improved |
| train MADNet with PointFix, MAD adaptation | MADNet · DrivingStereo weather, short-term | D1-all: 30.11 -> 9.48 | 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.
- CFNet — CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021) · 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
- Learning to Adapt for Stereo (CVPR 2019 · similarity 0.91)
- Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification (CVPR 2025 · similarity 0.86)
- RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo (NeurIPS 2025 · similarity 0.86)
- Robust Synthetic-to-Real Transfer for Stereo Matching (CVPR 2024 · similarity 0.86)
- Neural Markov Random Field for Stereo Matching (CVPR 2024 · 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.
