Research map / 3D vision / Depth and stereo
Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo
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 non-parametric depth modeling instead of a unimodal distribution while retaining standard cost aggregation (ablation) | DTU baseline · DTU | overall: 0.3425 -> 0.3590 | Hurt |
| Add sparse cost aggregation (ablation) | DTU unimodal baseline · DTU | overall: 0.3425 -> 0.3317 | Helped |
| Add sparse cost aggregation to non-parametric depth modeling (ablation) | DTU baseline with non-parametric modeling · DTU | overall: 0.3590 -> 0.3156 | Helped |
| Add non-parametric depth modeling to sparse cost aggregation (ablation) | DTU baseline with sparse cost aggregation · DTU | overall: 0.3317 -> 0.3156 | Helped |
| Use non-parametric depth distributions rather than the unimodal baseline (ablation) | DTU boundary depth estimation · DTU R0 | average depth error: 8.85 -> 6.48 | Helped |
| Use non-parametric multi-hypothesis depth modeling with sparse cost aggregation | MVS depth inference · Tanks and Temples | Mean f-score: 61.51 vs 59.64 | Mixed |
Closest papers by meaning
- Cost Volume Pyramid Based Depth Inference for Multi-View Stereo (CVPR 2020 · similarity 0.95)
- Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume (AAAI 2020 · similarity 0.90)
- Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation (AAAI 2023 · similarity 0.89)
- Generalized Binary Search Network for Highly-Efficient Multi-View Stereo (CVPR 2022 · similarity 0.89)
- Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (CVPR 2020 · similarity 0.89)
- Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation (CVPR 2022 · 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.