Research map / 3D vision / Human pose estimation
SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views
Chao Xu, Ang Li, Linghao Chen, Yulin Liu, Ruoxi Shi, Hao Su, Minghua Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 pose refinement against the generated mesh (n_init=1) (ablation) | SpaRP · GSO pose estimation | Rotation error: 13.02 -> 9.87 | Improved |
| increase mixture-of-experts initializations from 1 to 4 (ablation) | SpaRP pose estimation · GSO pose estimation | Rotation error: 9.87 -> 5.28 | Improved |
| increase experts from 1 to 8 (ablation) | SpaRP pose estimation · GSO ablation subset | Rotation error: 9.83 -> 4.34 | Improved |
| train pose (NOCS) and multi-view branches jointly with domain switcher (ablation) | SpaRP · GSO 500 objects | Rotation error: 9.87 -> 8.57 | Improved |
| joint training on reconstruction quality (ablation) | SpaRP · GSO 500 objects | PSNR: 19.03 -> 19.42 | Improved |
| increase number of input views from 1 to 6 (ablation) | SpaRP · GSO | F-Score (%): 89.1 -> 96.9 | Improved |
| use SpaRP instead of optimization-based iFusion with one initial pose | pose estimation · GSO pose estimation | Rotation error: 95.15 -> 9.87 | Improved |
| SpaRP without refinement versus iFusion with four initial poses | SpaRP · GSO pose estimation | Time: 256s -> 10s (similar accuracy) | Improved |
Later papers that compared with this method
1 later accepted paper reports SpaRP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes (ICCV 2025 · better on 5 of 5 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.92)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · similarity 0.91)
- LEAP: Liberate Sparse-View 3D Modeling from Camera Poses (ICLR 2024 · similarity 0.89)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.89)
- Cameras as Rays: Pose Estimation via Ray Diffusion (ICLR 2024 · similarity 0.89)
- SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction (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.
