Research map / 3D vision / Depth and stereo
CATS: A Color and Thermal Stereo Benchmark
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 |
|---|---|---|---|
| Use thermal-thermal rather than color-color stereo matching | Stereo matching algorithms evaluated on CATS · CATS thermal-thermal versus color-color | mean error (px) | Mixed |
| Use cross-modality rather than same-modality stereo matching | Stereo matching algorithms evaluated on CATS · CATS cross-modality | mean error (px) | Hurt |
| Use thermal stereo instead of color stereo in dark scenes | Stereo matching algorithms evaluated on CATS · Dark scenes | accuracy (τ=3) | Helped |
| Train MC-CNN on KITTI rather than Middlebury | MC-CNN · CATS color-color | accuracy (τ=3): 0.1133 -> 0.1354 | Helped |
Closest papers by meaning
- A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos (CVPR 2017 · similarity 0.88)
- Deep Depth Estimation From Thermal Image (CVPR 2023 · similarity 0.87)
- DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax (NeurIPS 2026 · similarity 0.86)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.85)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 2025 · similarity 0.84)
- HELVIPAD: A Real-World Dataset for Omnidirectional Stereo Depth Estimation (CVPR 2025 · similarity 0.84)
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.