Research map / 3D vision / Depth and stereo
Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells
Xinyi Ye, Weiyue Zhao, Tianqi Liu, Zihao Huang, Zhiguo Cao, Xin Li
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 |
|---|---|---|---|
| force saddle-shaped depth cells instead of one-sided cells at equal depth error | CasMVSNet depth maps · DTU toy experiment | Overall: 0.424 -> 0.246 | Improved |
| add Dual-Depth prediction (ablation) | CasMVSNet · DTU | Overall: 0.345 -> 0.320 | Improved |
| add Cascade Dual-Depths (ablation) | DMVSNet · DTU | Overall: 0.320 -> 0.313 | Improved |
| add checkerboard selection of min/max depth (ablation) | DMVSNet · DTU | Overall: 0.354 -> 0.320 | Improved |
| add L_int and L_sub losses (ablation) | DMVSNet · DTU | Overall: 0.337 -> 0.313 | Improved |
| add double 3D CNN branches (ablation) | DMVSNet · DTU | Overall: 0.327 -> 0.313 | Improved |
| use attention vs DCN features (lower depth error) | CasMVSNet · DTU | Overall vs depth error: depth err 9.15 vs 9.76; overall 0.343 vs 0.336 | Mixed |
| use DMVSNet with Dual-Depth on Tanks and Temples Advanced | DMVSNet · Tanks and Temples Advanced | mean F-score: 38.96 -> 41.17 | Improved |
| add dual-depth (doubled 3D CNN) compute cost | CasMVSNet · DTU | inference time (ms): 220 -> 424 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- transMVSNet — TransMVSNet: Global Context-Aware Multi-View Stereo Network With Transformers (CVPR 2022) · better on 1 of 2 shared results
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
- A Confidence-Based Iterative Solver of Depths and Surface Normals for Deep Multi-View Stereo (ICCV 2021 · similarity 0.91)
- Just a Few Points Are All You Need for Multi-View Stereo: A Novel Semi-Supervised Learning Method for Multi-View Stereo (ICCV 2021 · similarity 0.91)
- GeoMVSNet: Learning Multi-View Stereo With Geometry Perception (CVPR 2023 · similarity 0.90)
- Learning-Based Multi-View Stereo: A Survey (TPAMI 2026 · similarity 0.90)
- Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement (CVPR 2020 · similarity 0.90)
- DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo (AAAI 2025 · similarity 0.88)
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.
