Research map / 3D vision / NeRF and radiance fields
EfficientNeRF Efficient Neural Radiance Fields
Tao Hu, Shu Liu, Yilun Chen, Tiancheng Shen, Jiaya Jia
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 valid and pivotal sampling with NerfTree | EfficientNeRF · Realistic Synthetic | Training time (Hours): 56 -> 6 | Improved |
| Use valid and pivotal sampling with NerfTree | EfficientNeRF · Realistic Synthetic | Rendering speed (FPS): 0.023 -> 238.46 | Improved |
| Use valid and pivotal sampling with NerfTree | EfficientNeRF · Realistic Synthetic | PSNR: 31.01 -> 31.68 | Mixed |
| Use lightweight coarse MLP while retaining standard fine MLP (ablation) | NeRF · NeRF original pipeline | PSNR: 31.01 -> 30.96 | No clear effect |
| Use lightweight coarse MLP while retaining standard fine MLP (ablation) | NeRF · NeRF original pipeline | Time (s / iter): 0.184 -> 0.138 | Improved |
| Replace both coarse and fine MLPs with lightweight MLPs (ablation) | NeRF · NeRF original pipeline | PSNR: 31.01 -> 29.28 | Hurt |
| Replace standard fine MLP with lightweight fine MLP (ablation) | NeRF · NeRF original pipeline | PSNR: 31.01 -> 29.39 | Hurt |
| Add Spherical Harmonics color representation (ablation) | NeRF · Realistic Synthetic | PSNR: 31.01 -> 31.57 | Improved |
| Add lightweight coarse MLP (ablation) | NeRF + SH · Realistic Synthetic | Time (s / iter): 0.183 -> 0.137 | Improved |
| Add coarse valid sampling (ablation) | NeRF + lightweight coarse MLP · Realistic Synthetic | Time (s / iter): 0.137 -> 0.085 | Improved |
| Add fine pivotal sampling (ablation) | NeRF + coarse valid sampling · Realistic Synthetic | PSNR: 31.49 -> 31.68 | Improved |
| Add fine pivotal sampling (ablation) | NeRF + coarse valid sampling · Realistic Synthetic | Time (s / iter): 0.085 -> 0.021 | Improved |
Closest papers by meaning
- Efficient View Synthesis with Neural Radiance Distribution Field (ICCV 2023 · similarity 0.92)
- Neural Radiance Fields From Sparse RGB-D Images for High-Quality View Synthesis (TPAMI 2022 · similarity 0.92)
- CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis (AAAI 2025 · similarity 0.90)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.90)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.89)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.89)
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.
