Research map / 3D vision / Face and shape
LASR: Learning Articulated Shape Reconstruction From a Monocular Video
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 template-free LASR reconstruction instead of the strongest listed 3D reconstruction baseline | BADJA camel · BADJA camel | PCK-T: 49.7 -> 81.9 | Helped |
| Use template-free LASR reconstruction instead of the strongest listed 3D reconstruction baseline | BADJA dog · BADJA dog | PCK-T: 38.5 -> 65.8 | Helped |
| Use template-free LASR reconstruction instead of the strongest listed 3D reconstruction baseline | BADJA cows · BADJA cows | PCK-T: 70.0 -> 83.7 | Helped |
| Use template-free LASR reconstruction instead of the strongest listed 3D reconstruction baseline | BADJA horse · BADJA horse | PCK-T: 32.4 -> 49.3 | Helped |
| Use template-free LASR reconstruction instead of the strongest listed 3D reconstruction baseline | BADJA bear · BADJA bear | PCK-T: 67.2 -> 85.1 | Helped |
| Use GT masks rather than PointRend auto-masks | LASR on BADJA · BADJA animal videos | PCK-T: 81.9 vs 78.9 (camel); 65.8 vs 59.5 (dog); 83.7 vs 82.7 (cows); 49.3 vs 42.2 (horse); 85.1 vs 82.6 (bear) | Helped |
| Add optical-flow loss (ablation) | LASR rigid shape and camera optimization (S0) · Spot rigid object | Chamfer distance: 0.55 -> 0.05 | Helped |
| Add canonicalization loss (ablation) | LASR rigid shape and camera optimization (S0) · Spot rigid object | Chamfer distance: 0.61 -> 0.05 | Helped |
| Use CNN camera parameterization instead of directly optimizing camera poses (ablation) | LASR rigid shape and camera optimization (S0) · Spot rigid object | Chamfer distance: 0.63 -> 0.05 | Helped |
| Add linear blend skinning (ablation) | LASR articulated shape optimization (S0-S3) · Animated dog | Chamfer distance: 0.68 -> 0.28 | Helped |
| Use coarse-to-fine remeshing (ablation) | LASR articulated shape optimization (S0-S3) · Animated dog | Chamfer distance: 0.59 -> 0.28 | Helped |
| Use GMM skinning weights instead of an NxB weight matrix (ablation) | LASR articulated shape optimization (S0-S3) · Animated dog | Chamfer distance: 0.34 -> 0.28 | Helped |
Closest papers by meaning
- Learning Monocular 3D Reconstruction of Articulated Categories From Motion (CVPR 2021 · similarity 0.91)
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · similarity 0.90)
- S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video (ICML 2024 · similarity 0.89)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.89)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.87)
- REACTO: Reconstructing Articulated Objects from a Single Video (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.