Research map / 3D vision / NeRF and radiance fields
Learning Neural Duplex Radiance Fields for Real-Time View Synthesis
Ziyu Wan, Christian Richardt, Aljaž Božič, Chao Li, Vijay Rengarajan, Seonghyeon Nam, Xiaoyu Xiang, Tuotuo Li, Bo Zhu, Rakesh Ranjan, Jing Liao
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 duplex radiance rather than use one surface intersection (ablation) | NDRF · Synthetic-NeRF | PSNR: 26.95 -> 32.14 | Improved |
| Add convolutional shading rather than omit it (ablation) | NDRF · Synthetic-NeRF | PSNR: 30.03 -> 32.14 | Improved |
| Add multi-view distillation (ablation) | NDRF · Synthetic-NeRF | PSNR: 29.66 -> 32.14 | Improved |
| Increase convolution depth and receptive field (ablation) | NDRF · Fox | rendering quality | Hurt |
| Use additional mesh layers beyond the duplex pair (ablation) | NDRF · Synthetic-NeRF Chair | PSNR: 32.67 -> 32.84 | Improved |
| Use a single surface extracted at different density thresholds instead of duplex geometry (ablation) | NDRF · Synthetic-NeRF Ficus | PSNR: 28.01 -> 32.67 | Hurt |
| Distill from Instant-NGP instead of TensoRF (ablation) | NDRF · Synthetic-NeRF Chair | PSNR: 34.08 -> 34.17 | No clear effect |
| Convert the pretrained NeRF to rasterized NDRF WebGL | NeRF on Tanks&Temples · Tanks&Temples 1920×1080 | FPS: 0.01 -> 186.94 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- KiloNeRF — KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs (ICCV 2021) · better on 6 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis (ECCV 2022 · similarity 0.93)
- Efficient View Synthesis with Neural Radiance Distribution Field (ICCV 2023 · similarity 0.92)
- NeRFLight: Fast and Light Neural Radiance Fields Using a Shared Feature Grid (CVPR 2023 · similarity 0.92)
- Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis (TPAMI 2023 · similarity 0.92)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.91)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.91)
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.
