Research map / 3D vision / NeRF and radiance fields
NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu, Vitor Guizilini, Thomas Kollar, Adrien Gaidon, Zsolt Kira, Rares Ambrus
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 global triplane features to local features (ablation) | NeO 360 · NeRDS 360 (3 views) | PSNR: 17.50 -> 19.35 | Improved |
| add near/far background decomposition (ablation) | NeO 360 · NeRDS 360 (3 views) | PSNR: 19.02 -> 19.35 | Improved |
| use learned features instead of source-view colors directly (ablation) | NeO 360 · NeRDS 360 (3 views) | PSNR: 16.29 -> 19.35 | Improved |
| pretrain on 25 scenes (scene priors) instead of fitting from scratch (ablation) | NeO 360 · NeRDS 360 (3 views) | PSNR: absolute PSNR improvement of 4.08 | Improved |
| finetune triplane network on source views | NeO 360 · NeRDS 360 single map novel scenes, 3 views | PSNR: 19.35 -> 19.56 | Improved |
| increase source views from 1 to 5 | NeO 360 · NeRDS 360 single map novel scenes | PSNR: 17.60 -> 20.10 | Improved |
| naive triplanes without generative training (EG3D/GAUDI style) instead of local+global features | baseline comparison · NeRDS 360 (3 views) | PSNR: 12.84 vs 19.35 | Hurt |
Closest papers by meaning
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.88)
- 3D Reconstruction with Generalizable Neural Fields using Scene Priors (ICLR 2024 · similarity 0.88)
- LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias (ICLR 2025 · similarity 0.88)
- ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining (CVPR 2024 · similarity 0.88)
- Dynamic 3D Gaussian Fields for Urban Areas (NeurIPS 2024 · similarity 0.88)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · 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.
