Research map / 3D vision / NeRF and radiance fields
Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-Time
Liao Wang, Jiakai Zhang, Xinhang Liu, Fuqiang Zhao, Yanshun Zhang, Yingliang Zhang, Minye Wu, Jingyi Yu, Lan Xu
Check 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 |
|---|---|---|---|
| Use Fourier dimensions n1=31 and n2=5 instead of n1=11 and n2=5 (ablation) | FPO · Fourier dimension ablation | PSNR: 31.56 -> 36.21 | Improved |
| Increase n1 from 21 to 31 while keeping n2=5 (ablation) | FPO · Fourier dimension ablation | PSNR: 33.31 -> 36.21 | Improved |
| Increase n2 from 5 to 11 at n1=31 (ablation) | FPO · Fourier dimension ablation | PSNR: 36.21 -> 36.40 | Improved |
| Increase n2 from 5 to 11 at n1=31 (ablation) | FPO · Fourier dimension ablation | FPS: 117.87 -> 109.95 | Hurt |
| Increase n2 from 5 to 11 at n1=31 (ablation) | FPO · Fourier dimension ablation | Storage (GB): 7.251 -> 14.91 | Hurt |
| Add 10 minutes of fine-tuning rather than no fine-tuning (ablation) | FPO · Fine-tuning ablation | PSNR: 26.02 -> 32.93 | Improved |
| Extend fine-tuning from 10 minutes to 10 hours (ablation) | FPO · Fine-tuning ablation | PSNR: 32.93 -> 33.39 | No clear effect |
| Add DFT to the representation under limited memory (ablation) | FPO · FPO representation variants | PSNR: 25.97 -> 32.15 | Improved |
| Add DFT and use limited rather than unlimited memory (ablation) | FPO · FPO representation variants | PSNR: 32.39 -> 32.15 | No clear effect |
Closest papers by meaning
- PlenOctrees for Real-Time Rendering of Neural Radiance Fields (ICCV 2021 · similarity 0.92)
- Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF (ICCV 2023 · similarity 0.90)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.87)
- TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video (CVPR 2024 · similarity 0.87)
- Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields (AAAI 2024 · similarity 0.87)
- DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video (CVPR 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.
