Research map / 3D vision / 3D generation
ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
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 multiple views instead of a single view | Material estimation network · ABO material estimation test set | Roughness RMSE: 0.163 -> 0.129 | Helped |
| Add 3D projection alignment for neighboring views (ablation) | MV-net · ABO material estimation test set | Roughness RMSE: 0.155 -> 0.129 | Helped |
| Add 3D projection alignment for neighboring views (ablation) | MV-net · ABO material estimation test set | Normal similarity: 0.949 -> 0.976 | Helped |
| Train with deep metric learning rather than using ImageNet pretrained features | ABO-MVR · Rendered queries | Recall@1: 4.97 -> 30.02 | Helped |
| Use rendered queries instead of catalog queries | ABO-MVR Contrastive · ABO-MVR | Recall@1: 39.67 -> 28.56 | Hurt |
Closest papers by meaning
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.87)
- EA3D: Online Open-World 3D Object Extraction from Streaming Videos (NeurIPS 2025 · similarity 0.86)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.85)
- PICO: Reconstructing 3D People In Contact with Objects (CVPR 2025 · similarity 0.85)
- UnCommon Objects in 3D (CVPR 2025 · similarity 0.85)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.84)
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.