Research map / 3D vision / Depth and stereo
3D Scene Flow from 4D Light Field Gradients
Sizhuo Ma, Brandon M. Smith, Mohit Gupta
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 |
|---|---|---|---|
| estimate Z-motion directly with ray flow (CLG) instead of depth-based PD-Flow | scene flow · Single card translation stage | Z-flow MAE (mm): 0.250 -> 0.075 | Improved |
| estimate Z-motion directly with ray flow (CLG) instead of depth-based OLFW | scene flow · Single card translation stage | Z-flow MAE (mm): 0.420 -> 0.075 | Improved |
| CLG instead of PD-Flow for Z-motion | scene flow · Three cards translation stage | Z-flow MAE (mm): 0.507 -> 0.105 | Improved |
| CLG instead of OLFW for Z-motion | scene flow · Three cards translation stage | Z-flow MAE (mm): 1.751 -> 0.105 | Improved |
| CLG instead of OLFW for X-motion | scene flow · Three cards translation stage | X-flow MAE (mm): 0.308 -> 0.101 | Improved |
| CLG instead of PD-Flow for X-motion | scene flow · Single card translation stage | X-flow MAE (mm): 0.062 -> 0.068 | No clear effect |
| larger X motion (beyond 3.5 mm) for ray flow | CLG · Textured plane, X-motion | RMSE | Hurt |
| combine local and global ray flow (CLG) over individual local or global methods (ablation) | ray flow · qualitative scenes | accuracy | Improved |
| use ray-flow rather than depth-based methods for small axial motion | CLG vs PD-Flow/OLFW · Textured plane, Z-motion | RMSE | Improved |
Closest papers by meaning
- Differential Scene Flow from Light Field Gradients (IJCV 2019 · similarity 0.99)
- Depth Estimation Using Structured Light Flow -- Analysis of Projected Pattern Flow on an Object's Surface (ICCV 2017 · similarity 0.89)
- SEA-Flow3D: Simplified, Efficient, and Accurate Scene Flow via Spatial Vector Sampling and Multi-scale Refinement (CVPR 2026 · similarity 0.88)
- LiFF: Light Field Features in Scale and Depth (CVPR 2019 · similarity 0.87)
- A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras (TPAMI 2018 · similarity 0.87)
- Ray Space Features for Plenoptic Structure-From-Motion (ICCV 2017 · similarity 0.86)
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.
