Research map / 3D vision / Face and shape
Semantic Multi-View Stereo: Jointly Estimating Objects and Voxels
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 |
|---|---|---|---|
| Add an object shape prior | No prior [34] · LIVINGROOM | reconstruction accuracy | Helped |
| Add an object shape prior | No prior [34] · CAPITOL | reconstruction accuracy | Helped |
| Add an object shape prior | No prior [34] · DOWNTOWN and DOWNTOWN2 | reconstruction accuracy | Helped |
| Combine the object shape prior with the planarity prior (ablation) | Object shape prior · LIVINGROOM, CAPITOL, DOWNTOWN, and DOWNTOWN2 | reconstruction accuracy | Helped |
| Use an approximate IKEA shape model instead of the true object shape (ablation) | Object shape prior · LIVINGROOM | reconstruction accuracy | Hurt |
| Use approximate IKEA object models as shape priors (ablation) | No prior [34] · LIVINGROOM | reconstruction accuracy | Helped |
| Add an IKEA cupboard prior (ablation) | Object shape prior · LIVINGROOM | reconstruction accuracy | Hurt |
| Use a planarity prior instead of an object shape prior (ablation) | No prior [34] · CAPITOL | reconstruction accuracy | Helped |
| Use a planarity prior instead of an object shape prior (ablation) | No prior [34] · DOWNTOWN and DOWNTOWN2 with sufficiently many images | reconstruction accuracy | Mixed |
| Use only about 10 input images (ablation) | Object shape prior · Aerial datasets | reconstruction accuracy | Helped |
| Apply shape-model fitting after reconstructing with no prior, rather than jointly inferring shapes and voxels (ablation) | No prior [34] · DOWNTOWN | reconstruction accuracy | Hurt |
| Add object shape priors when only about 10 images are available (ablation) | No prior [34] · Aerial datasets | reconstruction accuracy | Helped |
Closest papers by meaning
- Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors (CVPR 2021 · similarity 0.89)
- Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (CVPR 2020 · similarity 0.89)
- 3DP3: 3D Scene Perception via Probabilistic Programming (NeurIPS 2021 · similarity 0.89)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.88)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.88)
- MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation (CVPR 2024 · similarity 0.87)
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.