Research map / 3D vision / Human pose estimation
A Real World Dataset for Multi-View 3D Reconstruction
Rakesh Shrestha, Siqi Hu, Minghao Gou, Ziyuan Liu, Ping Tan
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 |
|---|---|---|---|
| replace predicted depth with ground-truth depth | MeshMVS · real-world multi-view dataset | F1@0.3: 58.79 -> 90.85 | Improved |
| train on all categories jointly instead of single-category (ablation) | MV M-RCNN · real-world dataset mean | F1@0.3: 58.15 -> 64.77 | Improved |
| train on all categories jointly instead of single-category (ablation) | MV M-RCNN · real-world dataset mean | Chamfer: 10.57 -> 2.24 | Improved |
| train on all categories jointly instead of single-category (ablation) | MV M-RCNN · Toy Fruit | F1@0.3: 20.54 -> 59.84 | Improved |
| train on all categories jointly instead of single-category (ablation) | MV M-RCNN · Toy Car | F1@0.3: 65.18 -> 63.90 | Hurt |
| use Pixel2Mesh++ instead of MeshMVS (predicted depth) | real-world dataset · all categories | F1@0.3: 58.79 -> 73.30 | Improved |
| use IDR instead of DVR per-scene optimization | real-world dataset · 30 test scenes | F1@0.3: 79.56 -> 89.54 | Improved |
| use IDR instead of COLMAP | real-world dataset · 30 test scenes | F1@0.3: 39.81 -> 89.54 | Improved |
Closest papers by meaning
- Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction (ICCV 2021 · similarity 0.89)
- Real3D: Towards Scaling Large Reconstruction Models with Real Images (ICCV 2025 · similarity 0.89)
- OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation (CVPR 2023 · similarity 0.89)
- CAD-Estate: Large-scale CAD Model Annotation in RGB Videos (ICCV 2023 · similarity 0.88)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.87)
- Real2Code: Reconstruct Articulated Objects via Code Generation (ICLR 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.
