Research map / 3D vision / NeRF and radiance fields
SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory
Sicheng Li, Hao Li, Yue Wang, Yiyi Liao, Lu Yu
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 |
|---|---|---|---|
| Use SteerNeRF instead of Instant-NGP | NeRF rendering on Tanks & Temples · Tanks & Temples | FPS: 5.00 -> 27.24 | Improved |
| Use SteerNeRF instead of Instant-NGP | NeRF rendering on NeRF-Synthetic · NeRF-Synthetic | FPS: 35.41 -> 75.19 | Improved |
| Use SteerNeRF instead of Instant-NGP | NeRF rendering on Tanks & Temples · Tanks & Temples | PSNR (dB): 28.77 -> 28.65 | Hurt |
| Use SteerNeRF instead of Instant-NGP | NeRF rendering on NeRF-Synthetic · NeRF-Synthetic | PSNR (dB): 32.79 -> 31.60 | Hurt |
| Use two preceding frames rather than none (ablation) | SteerNeRF · Chair | PSNR (dB): 32.94 -> 33.14 | Improved |
| Use three preceding frames rather than two (ablation) | SteerNeRF · Chair | PSNR (dB): 33.14 -> 33.10 | Hurt |
| Use three feature channels rather than six (ablation) | SteerNeRF · Chair | PSNR (dB): 33.14 -> 32.53 | Hurt |
| Increase feature channels from six to nine (ablation) | SteerNeRF · Chair | PSNR (dB): 33.14 -> 33.21 | Improved |
| Jointly train neural feature fields and neural renderer (ablation) | SteerNeRF · Chair | PSNR (dB): 31.98 -> 33.05 | Improved |
| Reduce hash table length from 219 to 216 (ablation) | SteerNeRF neural feature fields · Chair | PSNR (dB): 33.05 -> 33.03 | No clear effect |
| Reduce hash table length from 219 to 214 (ablation) | SteerNeRF neural feature fields · Chair | PSNR (dB): 33.05 -> 32.70 | Hurt |
Closest papers by meaning
- A General Implicit Framework for Fast NeRF Composition and Rendering (AAAI 2024 · similarity 0.91)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.90)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.90)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 2025 · similarity 0.90)
- Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields (AAAI 2024 · similarity 0.90)
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.
