Research map / 3D vision / Depth and stereo
A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos
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 COLMAP instead of the other evaluated MVS methods | ETH3D MVS benchmarks · ETH3D high-resolution and mobile MVS | F1 score: 65.2; 64.1; 51.8; 69.7 | Helped |
| Evaluate methods on diverse scenes rather than only Strecha scenes | MVS methods · Strecha and ETH3D MVS benchmarks | F1 score: COLMAP 75.9 -> 64.7; CMPMVS 78.2 -> 48.9 | Mixed |
| Use video sequences with high view redundancy | PMVS, Gipuma, and CMPMVS · ETH3D low-resolution multi-view video | reconstruction accuracy and completeness | Hurt |
| Use MC-CNN on the ETH3D stereo benchmark instead of established stereo benchmarks | MC-CNN · ETH3D, Middlebury, and KITTI stereo | bad 2 ranking: 4 (8.9); 1 (10.1); 1 (3.9) | Mixed |
| Use the proposed image-to-laser-scan alignment refinement rather than initial alignment or 7-DoF ICP | Image and laser-scan registration · ETH3D registration examples | alignment quality | Helped |
Closest papers by meaning
- CATS: A Color and Thermal Stereo Benchmark (CVPR 2017 · similarity 0.88)
- MVSAnywhere: Zero-Shot Multi-View Stereo (CVPR 2025 · similarity 0.87)
- Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion (CVPR 2025 · similarity 0.87)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 2025 · similarity 0.87)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.86)
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction (CVPR 2025 · similarity 0.86)
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.