Research map / 3D vision / Depth and stereo
LiFF: Light Field Features in Scale and Depth
Donald G. Dansereau, Bernd Girod, Gordon Wetzstein
Check 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 |
|---|---|---|---|
| Use LiFF instead of SIFT | SfM with COLMAP defaults · Multi-view light-field scenes | % pass: 57.83 -> 64.19 | Improved |
| Use LiFF instead of SIFT | SfM with COLMAP permissive settings · Multi-view light-field scenes | % pass: 97.88 -> 97.53 | Hurt |
| Use LiFF instead of SIFT | SfM with COLMAP permissive settings · Multi-view light-field scenes | 3D Points: 396 -> 472 | Improved |
| Use LiFF instead of SIFT | SfM on scenes both methods reconstruct with COLMAP defaults · Defaults Intersect | Inlier Matches / Img: 240 -> 297 | Improved |
| Use LiFF instead of SIFT | SfM on scenes both methods reconstruct with COLMAP permissive settings · Permissive Intersect | 3D Points: 397 -> 473 | Improved |
| Use LiFF instead of repeated SIFT | Feature detection and descriptor extraction · Lytro Illum light fields | runtime: 53.1 sec -> 2.88 sec | Improved |
| Jointly search scale and slope in the light field | LiFF feature detection · Synthetic disks under high noise | true positive rate | Improved |
| Detect blobs using LiFF rather than SIFT or repeated SIFT | Synthetic disks with varying noise · Synthetic disks | noise tolerance | Improved |
Closest papers by meaning
- SynLF: Zero-Shot Metric Depth from Light Field Cameras via Physics-Grounded Synthesis (ECCV 2026 · similarity 0.87)
- Shape Estimation from Shading, Defocus, and Correspondence Using Light-Field Angular Coherence (TPAMI 2016 · similarity 0.87)
- 3D Scene Flow from 4D Light Field Gradients (ECCV 2018 · similarity 0.87)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.87)
- Large-Scale, Metric Structure From Motion for Unordered Light Fields (CVPR 2019 · similarity 0.87)
- Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering (NeurIPS 2021 · similarity 0.87)
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.
