Research map / 3D vision / Depth and stereo
DPSNet: End-to-end Deep Plane Sweep Stereo
Read the paperCheck 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 concatenated features instead of absolute-difference features (ablation) | DPSNet · MVS, SUN3D, RGBD, Scenes11 | RMSE: 0.5484 -> 0.5207 | Helped |
| add cost aggregation (ablation) | DPSNet · MVS, SUN3D, RGBD, Scenes11 | RMSE: 0.6230 -> 0.5207 | Helped |
| replace stacked-hourglass aggregation with reference-feature-guided aggregation (ablation) | DPSNet · MVS, SUN3D, RGBD, Scenes11 | RMSE: 0.5306 -> 0.5207 | Helped |
| sample planes uniformly in inverse depth instead of uniformly in depth (ablation) | DPSNet · MVS, SUN3D, RGBD, Scenes11 | RMSE: 0.5951 -> 0.5207 | Helped |
Closest papers by meaning
- MVS2D: Efficient Multi-View Stereo via Attention-Driven 2D Convolutions (CVPR 2022 · similarity 0.88)
- StereoDRNet: Dilated Residual StereoNet (CVPR 2019 · similarity 0.88)
- DeepMVS: Learning Multi-View Stereopsis (CVPR 2018 · similarity 0.88)
- PlaneMVS: 3D Plane Reconstruction From Multi-View Stereo (CVPR 2022 · similarity 0.87)
- Cost Volume Pyramid Based Depth Inference for Multi-View Stereo (CVPR 2020 · similarity 0.87)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.85)
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.