Research map / 3D vision / NeRF and radiance fields
Structured-NeRF: Hierarchical Scene Graph with Neural Representation
Zhide Zhong, Jiakai Cao, songen gu, Sirui Xie, Liyi Luo, Hao Zhao, Guyue Zhou, Haoang Li, Zike Yan
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 inpainted pseudo depth supervision for the background (ablation) | Structured-NeRF · ScanNet scene 0113_00 | PSNR: 30.68 -> 31.95 | Improved |
| add inpainted pseudo RGBD supervision for the background (ablation) | Structured-NeRF · ScanNet scene 0113_00 | PSNR: PSNR 31.69 -> 31.95; LPIPS 0.2019 -> 0.2057 | Mixed |
| add object accumulation loss (ablation) | Structured-NeRF · ScanNet scene 0113_00 | PSNR: 30.99 -> 31.95 | Improved |
| add object RGB loss together with inpainted RGBD supervision (ablation) | Structured-NeRF · ScanNet scene 0113_00 | PSNR: 31.31 -> 31.95 | Improved |
| use hierarchical scene-graph NeRF instead of UDC-NeRF for rendering | Structured-NeRF · ScanNet | PSNR: 26.135 -> 30.360 | Improved |
| use scene-graph-driven re-arrangement instead of Stable Diffusion or DALL-E-NeRF | Structured-NeRF · Kitchen re-arrangement | FID: 221.62 -> 197.22 | Improved |
| scene-graph re-arrangement versus DALL-E-NeRF on office KID | Structured-NeRF · Office re-arrangement | KID: 0.04 -> 0.04 | No clear effect |
Closest papers by meaning
- Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering (ICCV 2021 · similarity 0.91)
- Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis (ICCV 2023 · similarity 0.91)
- Editing Conditional Radiance Fields (ICCV 2021 · similarity 0.90)
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields (CVPR 2024 · similarity 0.88)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.88)
- A Pre-convolved Representation for Plug-and-Play Neural Illumination Fields (AAAI 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.
