Research map / 3D vision / Face and shape
Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category Reconstruction
Jeremy Reizenstein, Roman Shapovalov, Philipp Henzler, Luca Sbordone, Patrick Labatut, David Novotny
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 Warp-conditioned Embedding (WCE) | NeRF · CO3D single-scene | PSNR: 23.6 -> 21.0 | Hurt |
| add WCE | SRN · CO3D 10 categories test-unseen vs NerFormer | PSNR: 17.6 -> 14.6 | Hurt |
| add positional embedding gamma and WCE to SRN | SRN · CO3D single-scene | PSNR: 15.8 -> 16.9 | Mixed |
| add positional embedding gamma to SRN+WCE (ablation) | SRN+WCE · CO3D 10 categories train-unseen | PSNR: 16.6 -> 17.6 | Improved |
| add positional embedding gamma to SRN+WCE (ablation) | SRN+WCE · CO3D 10 categories test-unseen | PSNR: 14.6 -> 14.4 | No clear effect |
| use NerFormer attention instead of WCE-only NeRF | NeRF+WCE · CO3D 10 categories test-unseen | PSNR: 13.8 -> 17.6 | Improved |
| use opacity-based NeRF instead of SDF-based IDR | single-scene · CO3D single-scene | PSNR: 18.5 -> 23.6 | Improved |
| use mesh representation (P3DMesh) instead of implicit methods | category-centric · CO3D 10 categories test-unseen | PSNR: 17.6 -> 12.4 | Hurt |
| use autodecoder test-time latent optimization instead of NerFormer | NeRF+AD · CO3D test-unseen | PSNR: 17.6 -> 10.6 | Hurt |
| increase number of source views from 1 to 9 | NerFormer · CO3D 10 categories test-unseen | PSNR: 15.1 -> 18.9 | Improved |
| use autodecoder SRN+gamma+AD instead of NerFormer | category-centric · CO3D 10 categories train-unseen | PSNR: 17.9 -> 21.7 | Improved |
| evaluate on all 50 categories rather than 10 | NerFormer · CO3D test-unseen | PSNR: 17.6 -> 15.7 | Mixed |
Closest papers by meaning
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.91)
- UnCommon Objects in 3D (CVPR 2025 · similarity 0.90)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.89)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.89)
- Large-Vocabulary 3D Diffusion Model with Transformer (ICLR 2024 · similarity 0.88)
- RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos (CVPR 2024 · 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.
