Research map / 3D vision / Human pose estimation
CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose
Li Jin, Yuchen Yang, Weikai Chen, Yujie Wang, Dehao Hao, Tanghui Jia, Yingda Yin, Zeyu HU, Runze Zhang, Keyang Luo, Li Yuan, Long Quan and 2 more
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 |
|---|---|---|---|
| train on canonical CanoVerse instead of Objaverse-OA | VI-Net · CanoVerse in-distribution | Acc@10deg: 21.77 -> 55.31 | Improved |
| train on CanoVerse instead of Objaverse-OA | VI-Net · OmniObject3D OOD | Acc@10deg: 6.56 -> 20.18 | Improved |
| add canonicalization to fine-tuning data (ablation) | Trellis · Toys4K | Chamfer Distance: 0.227 -> 0.095 | Improved |
| add canonicalization to fine-tuning data (ablation) | Trellis · Toys4K | IQR of angular error: 48.5 -> 7.7 | Improved |
| add canonicalization to fine-tuning data (ablation) | Hunyuan3D 2.1 · Toys4K | IQR of angular error: 75.59 -> 8.1 | Improved |
| add canonicalization to fine-tuning data (ablation) | Hunyuan3D 2.1 · GSO | IQR of angular error: 74.02 -> 18.6 | Improved |
| add canonicalization to training data (ablation) | Uni3D · CanoVerse image retrieval | Recall@10: 79.07 -> 81.82 | Improved |
| add canonicalization to training data (ablation) | ULIP · CanoVerse text retrieval | Recall@10: 21.33 -> 25.05 | Improved |
| add canonicalization to training data (ablation) | Uni3D · OmniObject3D text retrieval | Recall@10: 34.21 -> 35.88 | Improved |
| use CanoVerse candidate generation plus one-click selection instead of manual Blender alignment | annotation pipeline · annotation speed (high-skill) | seconds per object: 94.5 -> 2.6 | Improved |
| use CanoVerse pipeline instead of COD | annotation pipeline · DREDS | IC: 0.194 -> 0.032 | Improved |
| use CanoVerse pipeline instead of COD | annotation pipeline · DREDS Aeroplane | IC: 0.051 -> 0.129 | Hurt |
Closest papers by meaning
- One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency (CVPR 2025 · similarity 0.90)
- Orientation Matters: Making 3D Generative Models Orientation-Aligned (NeurIPS 2025 · similarity 0.88)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.87)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.86)
- SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE (CVPR 2025 · similarity 0.86)
- Tango3D: Towards Alignment for Global and Local 2D-3D Correspondence (NeurIPS 2026 · 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.
