Research map / 3D vision / NeRF and radiance fields
SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang
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 geometry pseudo labels L_geo (ablation) | SinNeRF · Lego | PSNR: 16.11 -> 20.97 | Improved |
| add global structure prior L_cls (ablation) | SinNeRF · Lego | PSNR: 18.20 -> 20.97 | Improved |
| add adversarial training L_adv (ablation) | SinNeRF · Lego | PSNR: 20.20 -> 20.97 | Improved |
| add L_adv (LPIPS) (ablation) | SinNeRF · Lego | LPIPS: 0.1306 -> 0.0932 | Improved |
| use DINO-ViT [CLS] prior instead of style loss (ablation) | SinNeRF · Lego | PSNR: 15.49 -> 20.97 | Improved |
| use DINO-ViT [CLS] prior instead of self-similarity loss (ablation) | SinNeRF · Lego | PSNR: 18.67 -> 20.97 | Improved |
| use DINO-ViT [CLS] prior instead of content loss (ablation) | SinNeRF · Lego | PSNR: 19.20 -> 20.97 | Improved |
| SinNeRF vs best baseline DietNeRF | SinNeRF · DTU (single view, average) | PSNR: 12.84 -> 16.52 | Improved |
Later papers that compared with this method
7 later accepted papers report SinNeRF as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- PERF: Panoramic Neural Radiance Field From a Single Panorama (TPAMI 2024 · better on 4 of 4 shared results)
- Viewpoint textual inversion: discovering scene representations and 3D view control in 2D diffusion models (ECCV 2024 · better on 1 of 3 shared results)
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image (CVPR 2024 · better on 0 of 2 shared results)
- From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos (NeurIPS 2024 · better on 1 of 2 shared results)
- RealFusion: 360deg Reconstruction of Any Object From a Single Image (CVPR 2023 · better on 0 of 3 shared results)
- NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views (CVPR 2023 · better on 1 of 1 shared result)
- Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior (ICCV 2023 · better on 1 of 1 shared result)
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
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.91)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.91)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 2024 · similarity 0.91)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 2024 · similarity 0.91)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.90)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (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.
