Research map / 3D vision / NeRF and radiance fields
A Large-Scale Outdoor Multi-Modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction
Chongshan Lu, Fukun Yin, Xin Chen, Wen Liu, Tao Chen, Gang Yu, Jiayuan Fan
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 textual prompts via text-based coordinate attention to NeRF (ablation) | NeRF · OMMO (mean) | PSNR: 18.72 -> 19.01 | Improved |
| add textual prompts via text-based coordinate attention to CoCo-INR (ablation) | CoCo-INR · OMMO (mean) | PSNR: 16.80 -> 16.97 | Improved |
| train and test on night scenes versus day scenes | NeRF · OMMO sub-benchmark by lighting | PSNR: 18.37 -> 22.24 | Improved |
| circular versus irregular camera trajectories | NeRF methods · OMMO sub-benchmark by camera track | PSNR: Mip-NeRF 360 irregular 21.05 vs circles 23.81 | Improved |
| larger scene scale (cities versus small areas) | NeRF methods · OMMO sub-benchmark by scene type | PSNR: Mip-NeRF 360 small areas 24.89 vs cities 20.44 | Hurt |
| use Mip-NeRF 360 instead of other NeRF variants | outdoor novel view synthesis · OMMO (mean) | PSNR: 23.10 vs 21.63 (Mega-NeRF) | Improved |
| use vanilla NeRF on scenes with irregular trajectories | NeRF · OMMO scenes 7, 26, 27, 33 | PSNR: 5.36, 8.56, 4.54, 5.79 | Hurt |
Closest papers by meaning
- SUDS: Scalable Urban Dynamic Scenes (CVPR 2023 · similarity 0.91)
- S-NeRF: Neural Radiance Fields for Street Views (ICLR 2023 · similarity 0.90)
- Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields (ICLR 2023 · similarity 0.90)
- MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond (ICCV 2023 · similarity 0.90)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.88)
- Multi-Level Neural Scene Graphs for Dynamic Urban Environments (CVPR 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.
