Research map / 3D vision / Depth and stereo
Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity
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 multiple resolutions in a coarse-to-fine strategy instead of only 1/8 resolution (ablation) | DispMVS · DTUMVS | Overall: 0.455 -> 0.339 | Helped |
| Vary the random depth initialization across inference runs (ablation) | DispMVS · DTUMVS | Overall: 0.338970; 0.339878; 0.339298 | No clear effect |
| Use an epipolar 2D cost volume rather than a depth-range-dependent 3D cost volume | MVS depth estimation · DTUMVS, changed depth ranges | Overall: DispMVS: 0.339 -> 0.376 -> 0.493; GBiNet: 0.289 -> 0.518 -> 0.960; IterMVS: 0.363 -> 1.002 -> 3.960 | Mixed |
Closest papers by meaning
- A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding (NeurIPS 2024 · similarity 0.90)
- DispViT: Direct Stereo Disparity Regression with a Single-Stream Vision Transformer (ICLR 2026 · similarity 0.90)
- MVS2D: Efficient Multi-View Stereo via Attention-Driven 2D Convolutions (CVPR 2022 · similarity 0.90)
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (CVPR 2020 · similarity 0.89)
- DeepMVS: Learning Multi-View Stereopsis (CVPR 2018 · similarity 0.89)
- MVSAnywhere: Zero-Shot Multi-View Stereo (CVPR 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.