Research map / 3D vision / 3D generation
Equivariant Neural Rendering
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 |
|---|---|---|---|
| Use Equivariant Neural Rendering instead of TCO | Single-shot novel view synthesis · ShapeNet chairs | PSNR (dB): 21.27 vs 20.41 | Hurt |
| Use Equivariant Neural Rendering instead of dGQN | Single-shot novel view synthesis · ShapeNet chairs | PSNR (dB): 21.59 vs 20.41 | Hurt |
| Use invertible shear rotations rather than naive tensor rotations | Equivariant Neural Rendering · CIFAR10 rotation round-trip diagnostic | mean pixel value error: 3% | Helped |
Closest papers by meaning
- Neural Scene Graphs for Dynamic Scenes (CVPR 2021 · similarity 0.90)
- Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior (NeurIPS 2022 · similarity 0.89)
- 3D-Aware Scene Manipulation via Inverse Graphics (NeurIPS 2018 · similarity 0.89)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.89)
- $SE(3)$ Equivariant Convolution and Transformer in Ray Space (NeurIPS 2023 · similarity 0.89)
- Real3D: The Curious Case of Neural Scene Degeneration (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.