Research map / 3D vision / Face and shape
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
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 continuous 3D-structure-aware scene representations with differentiable ray marching instead of the strongest reported baseline | Novel-view synthesis · ShapeNet v2 chairs, 50 images (training set) | PSNR (dB): 24.57 -> 26.23 | Helped |
| Use continuous 3D-structure-aware scene representations with differentiable ray marching instead of the strongest reported baseline | Novel-view synthesis · ShapeNet v2 cars, 50 images (training set) | PSNR (dB): 20.38 -> 26.32 | Helped |
| Use continuous 3D-structure-aware scene representations with differentiable ray marching instead of the strongest reported baseline | Few-shot reconstruction · ShapeNet v2 chairs, 2 images | PSNR (dB): 22.36 -> 24.48 | Helped |
| Use continuous 3D-structure-aware scene representations with differentiable ray marching instead of the strongest reported baseline | Few-shot reconstruction · ShapeNet v2 cars, 2 images | PSNR (dB): 18.79 -> 22.94 | Helped |
| Use continuous 3D-structure-aware scene representations with differentiable ray marching instead of the strongest reported baseline | Few-shot reconstruction · ShapeNet v2 chairs, single image | PSNR (dB): 21.27 -> 22.89 | Helped |
| Use continuous 3D-structure-aware scene representations with differentiable ray marching instead of the strongest reported baseline | Few-shot reconstruction · ShapeNet v2 cars, single image | PSNR (dB): 18.19 -> 20.72 | Helped |
| Use continuous 3D-structure-aware scene representations instead of dGQN | Novel-view synthesis · Shepard-Metzler training objects, 15 observations | PSNR (dB): 20.85 -> 30.41 | Helped |
| Use continuous 3D-structure-aware scene representations instead of dGQN | Few-shot reconstruction · Shepard-Metzler held-out objects, two-shot | PSNR (dB): 18.56 -> 24.36 | Helped |
| Use continuous 3D-structure-aware scene representations instead of dGQN | Few-shot reconstruction · Shepard-Metzler held-out objects, one-shot | PSNR (dB): 17.51 -> 18.11 | Helped |
Closest papers by meaning
- Neural Scene Graphs for Dynamic Scenes (CVPR 2021 · similarity 0.89)
- Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations (CVPR 2022 · similarity 0.89)
- BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images (NeurIPS 2020 · similarity 0.88)
- Equivariant Neural Rendering (ICML 2020 · similarity 0.88)
- Geometry-Aware Deep Network for Single-Image Novel View Synthesis (CVPR 2018 · similarity 0.88)
- OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos (ICML 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.