Research map / 3D vision / NeRF and radiance fields
Shape, Pose, and Appearance From a Single Image via Bootstrapped Radiance Field Inversion
Read the paperCheck 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 30-step hybrid inversion to the encoder initialization | Ours · Pascal3D+ Cars | IoU: 0.883 -> 0.920 | Helped |
| Add 30-step hybrid inversion to the encoder initialization | Ours · CUB Birds | FID: 28.15 -> 24.70 | Helped |
| Add hybrid inversion | Ours · ImageNet categories | IoU | Helped |
| Add hybrid inversion | Ours · ImageNet Airplane and Zebra | FID: 18.77 -> 19.78; 21.58 -> 24.47 | Hurt |
| Use predicted poses instead of dataset poses (ablation) | Ours (N=0) · Pascal3D+ Cars | IoU: 0.803 -> 0.883 | Helped |
| Use predicted poses instead of dataset poses (ablation) | Ours (N=30) · Pascal3D+ Cars | IoU: 0.802 -> 0.920 | Helped |
| Use predicted poses instead of dataset poses (ablation) | Ours · Pascal3D+ Cars | FID: 73.20 (16.39) -> 75.90 (15.08); 72.22 (15.10) -> 73.53 (14.36) | Mixed |
| Add path length regularization (ablation) | Ours hybrid inversion · Pascal3D+ Cars | FID | Helped |
| Add color mapping (ablation) | Ours hybrid inversion · Pascal3D+ Cars | PSNR | Helped |
| Use the proposed SDF-based backbone instead of vanilla EG3D (ablation) | Ours backbone · ShapeNet Chairs | PSNR | Helped |
| Use SDF representation instead of volume density (ablation) | Ours generator · Pascal3D+ Cars | FID | Helped |
| Use hybrid inversion instead of the encoder-based approach (ablation) | Ours · ShapeNet Chairs | PSNR | Helped |
Closest papers by meaning
- Sharf: Shape-conditioned Radiance Fields from a Single View (ICML 2021 · similarity 0.90)
- Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation (CVPR 2022 · similarity 0.90)
- A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose (NeurIPS 2021 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.88)
- ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization (CVPR 2024 · similarity 0.88)
- ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field (NeurIPS 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.