Datasets › LLFF
LLFF (Local Light Field Fusion)
Local Light Field Fusion (LLFF) is a practical and robust deep learning solution for capturing and rendering novel views of complex real-world scenes for virtual exploration. The dataset consists of both renderings and real images of natural scenes. The synthetic images are rendered from the SUNCG and UnrealCV where SUNCG contains 45000 simplistic house and room environments with texture-mapped surfaces and low geometric complexity. UnrealCV contains a few large-scale environments modeled and rendered with extreme detail. The real images are 24 scenes captured from a handheld cellphone.
Benchmarks archive 2025-07-28
All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Novel View Synthesis | LLFF | TensoRF + NeRFLiX PSNR 27.39 | NeRFLiX: High-Quality Neural View Synthesis by Learning... | redrock303/NeRFLiX_CPVR2023 | 15 | Compare |
| 3D Object Editing | LLFF | CE3D CLIP 0.9 | Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts | Fangkang515/CE3D | 1 | Compare |
| 3D scene Editing | LLFF | CE3D CLIP 0.99 | Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts | Fangkang515/CE3D | 1 | Compare |
| 3D Shape Reconstruction From A Single 2D Image | LLFF | Chat-Edit-3D CLIP 0.9 | Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts | Fangkang515/CE3D | 1 | Compare |
Papers archive 2025-07-28
5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 340. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts | 1 | 3 | 9 Jul 2024 | not harvested |
| NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer | 1 | 2 | 13 Mar 2023 | not harvested |
| K-Planes: Explicit Radiance Fields in Space, Time, and Appearance | 2 | 4 | 24 Jan 2023 | ran 1 of 1 samples (0 unverified) |
| HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling | 1 | 5 | 5 Jan 2023 | ran 7 of 11 samples (4 unverified) |
| MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures | 1 | 4 | 30 Jul 2022 | ran 0 of 9 samples (9 unverified) |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
No modality tagged.
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- LLFF
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections