Research map / Label-efficient and robust learning / Recognition and long-tail
DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Train DispNet on DrivingStereo instead of Cityscapes | DispNet · KITTI Stereo 2015 | EPE: 1.91 -> 1.24 | Helped |
| Train DispNet on DrivingStereo instead of Cityscapes | DispNet · KITTI Stereo 2015 | D1 Error: 14.66% -> 6.30% | Helped |
| Train DispNet on DrivingStereo instead of Cityscapes | DispNet · KITTI Stereo 2015 | GD: 17.77% -> 14.04% | Helped |
| Train DispNet on DrivingStereo instead of Cityscapes | DispNet · DrivingStereo test set | EPE: 3.59 -> 1.93 | Helped |
| Train DispNet on DrivingStereo instead of Cityscapes | DispNet · DrivingStereo test set | D1 Error: 34.15% -> 16.82% | Helped |
| Train DispNet on DrivingStereo instead of Cityscapes | DispNet · DrivingStereo test set | GD: 10.47% -> 7.02% | Helped |
| Use distance-aware and semantic-aware metrics alongside overall EPE and D1 | Stereo matching evaluation · Driving scenes across distances and semantic classes | Evaluation coverage | Helped |
Closest papers by meaning
- LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving (CVPR 2026 · similarity 0.91)
- One Million Scenes for Autonomous Driving: ONCE Dataset (NeurIPS 2021 · similarity 0.91)
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset (CVPR 2020 · similarity 0.90)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.88)
- The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (NeurIPS 2026 · similarity 0.88)
- DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation (CVPR 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.