Research map / 3D vision / NeRF and radiance fields
AutoRF: Learning 3D Object Radiance Fields From Single View Observations
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 |
|---|---|---|---|
| Add test-time optimization of the shape and appearance codes (ablation) | AutoRF · nuScenes cars validation | PSNR: 18.69 -> 18.94 | Helped |
| Add test-time optimization of the shape and appearance codes (ablation) | AutoRF · SRN-Cars | PSNR: 18.08 -> 19.66 | Helped |
| Train with machine-generated rather than human annotations (ablation) | AutoRF · nuScenes cars validation | PSNR: 18.95 -> 18.94 | No clear effect |
| Train with human-annotated data instead of machine-annotated data (ablation) | AutoRF · nuScenes cars validation | FID: 145.10 -> 106.50 | Helped |
| Add 5°/10cm perturbations to the annotations (ablation) | AutoRF · nuScenes cars validation | PSNR: 18.95 -> 18.67 | Hurt |
| Add 10°/20cm perturbations to the annotations (ablation) | AutoRF · nuScenes cars validation | PSNR: 18.95 -> 17.95 | Hurt |
| Add 20°/40cm perturbations to the annotations (ablation) | AutoRF · nuScenes cars validation | PSNR: 18.95 -> 16.83 | Hurt |
| Train the object representation from single-view observations rather than multi-view instance constraints | AutoRF · nuScenes cars validation | PSNR: 18.25 -> 18.69 | Helped |
Closest papers by meaning
- Sharf: Shape-conditioned Radiance Fields from a Single View (ICML 2021 · similarity 0.91)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.90)
- To View Transform or Not to View Transform: NeRF-based Pre-training Perspective (ICLR 2026 · similarity 0.89)
- DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features (NeurIPS 2024 · similarity 0.87)
- MuRF: Multi-Baseline Radiance Fields (CVPR 2024 · similarity 0.87)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.87)
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.