Research map / 3D vision / Depth and stereo
On Joint Estimation of Pose, Geometry and svBRDF From a Handheld Scanner
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 |
|---|---|---|---|
| Jointly optimize camera poses with geometry and materials rather than fixing poses (ablation) | Handheld scanner reconstruction · Overall test views | photometric test error: 1.210 -> 1.138 | Helped |
| Jointly optimize camera poses with geometry and materials rather than fixing poses (ablation) | Handheld scanner reconstruction · Specular regions | photometric test error: 3.349 -> 3.243 | Helped |
| Jointly optimize camera poses with geometry and materials rather than fixing poses (ablation) | Handheld scanner reconstruction · Non-specular regions | photometric test error: 1.151 -> 1.081 | Helped |
| Add joint rather than alternating geometry and material optimization (ablation) | Handheld scanner reconstruction · Most evaluated objects | geometry accuracy | Helped |
| Add geometric consistency coupling depth and normals (ablation) | Handheld scanner reconstruction · Object geometry | geometric consistency | Helped |
| Add non-local material smoothness regularization (ablation) | Handheld scanner reconstruction · Held-out illumination conditions | photometric reconstruction quality | Helped |
| Add non-local material smoothness regularization (ablation) | Handheld scanner reconstruction · Homogeneous object regions | material consistency | Helped |
| Reduce the number of input views (ablation) | Proposed method · Photometric test views | photometric test error | Hurt |
| Reduce the number of input views (ablation) | Proposed method · Specular highlights | highlight reconstruction quality | Hurt |
| Initialize geometry from only 5 depth maps instead of 40 (ablation) | Proposed method · Object geometry | reconstruction quality | No clear effect |
Closest papers by meaning
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.86)
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.86)
- RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects (CVPR 2025 · similarity 0.85)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.84)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.84)
- GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence (CVPR 2024 · similarity 0.84)
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.