Research map / 3D vision / Human pose estimation
UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
Chuanrui Zhang, Yingshuang Zou, ZhengXian Wu, Yonggen Ling, Yuxiao Yang, Ziwei Wang
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-Aware Shape Representation (PASR) in place of canonical shape reconstruction (ablation) | UniPR · LVS6D Hard subset | ACD: 12.363 -> 1.224 | Improved |
| add PASR to the Coders baseline (ablation) | Coders · LVS6D Hard subset | ACD: 10.146 -> 1.816 | Improved |
| use stereo input instead of left image only (ablation) | UniPR · LVS6D Hard subset | AP: 0.270 -> 0.752 | Improved |
| use spherical voxel space instead of cubic (ablation) | UniPR · LVS6D Hard subset | AP / ACD: AP 0.677 -> 0.752; ACD 1.310 -> 1.224; APE 1.129 -> 1.248 | Mixed |
| end-to-end whole-scene single pass versus per-object image-to-3D pipelines | UniPR · 5-object scene | Inference time (s): 370.78 -> 0.63 | Improved |
| use UniPR instead of Trellis/Hunyuan2.1 given GT masks and poses | shape reconstruction · LVS6D reconstruction (50 objects) | Shape Proportion Error: 0.320 -> 0.109 | Improved |
| UniPR with pose decoding layer versus Coders on TOD | UniPR · TOD | 3D50: 99.8 -> 97.5 | Hurt |
Closest papers by meaning
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.87)
- DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024 · similarity 0.86)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.86)
- UniK3D: Universal Camera Monocular 3D Estimation (CVPR 2025 · similarity 0.86)
- MUSt3R: Multi-view Network for Stereo 3D Reconstruction (CVPR 2025 · similarity 0.86)
- Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors (CVPR 2025 · similarity 0.86)
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.
