Research map / 3D vision / Depth and stereo
Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions
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 locally adaptive radiometric alignment and complementary stereo cues with a color–monochrome camera pair | Proposed stereo matching method · Controlled indoor scene, bright illumination | bad pixel rate: 11.79% | Helped |
| Use locally adaptive radiometric alignment and complementary stereo cues with a color–monochrome camera pair | Proposed stereo matching method · Controlled indoor scene, dark illumination | bad pixel rate: 14.48% | Helped |
| Remove normalized sparsity from decolorization parameter selection (ablation) | Proposed stereo matching method · Middlebury stereo benchmark, Setup 1 and Setup 2 | bad pixel rate | Hurt |
| Remove informative-edge similarity from the stereo matching cost (ablation) | Proposed stereo matching method · Middlebury stereo benchmark, Setup 1 and Setup 2 | bad pixel rate | Hurt |
| Add chrominance consistency weighting to colorization (ablation) | Proposed color recovery · Middlebury stereo benchmark colorization evaluation | PSNR | Helped |
| Add chrominance consistency weighting to colorization (ablation) | Proposed color recovery · Middlebury stereo benchmark colorization evaluation | SSIM | Helped |
Closest papers by meaning
- Deep Material-Aware Cross-Spectral Stereo Matching (CVPR 2018 · similarity 0.88)
- Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light (CVPR 2022 · similarity 0.88)
- CATS: A Color and Thermal Stereo Benchmark (CVPR 2017 · similarity 0.87)
- Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues (CVPR 2025 · similarity 0.84)
- Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail (CVPR 2025 · similarity 0.84)
- MonSter: Marry Monodepth to Stereo Unleashes Power (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.