Research map / Architectures and efficiency / RNNs and normalization
Filter Flow Made Practical: Massively Parallel and Lock-Free
Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh
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 |
|---|---|---|---|
| Reformulate Filter Flow with convex compactness and structure-exploiting optimization | Filter Flow · Filter Flow vision applications | runtime: 30 times faster | Improved |
| Use the parallel implementation instead of the sequential implementation | F3-MPLF · 640×480 image pair | runtime: ≈2 hours -> ≈10 minutes | Improved |
| Use F3-MPLF instead of FullFlow | Optical flow · MPI Sintel test, Final pass, all | AEE: 5.895 -> 6.272 | Hurt |
| Use F3-MPLF instead of DiscreteFlow | Optical flow · MPI Sintel test, Clean pass, all | AEE: 3.567 -> 4.770 | Hurt |
Closest papers by meaning
- SceneFlowFields++: Multi-frame Matching, Visibility Prediction, and Robust Interpolation for Scene Flow Estimation (IJCV 2019 · similarity 0.86)
- Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Vision (TPAMI 2022 · similarity 0.86)
- Solving Vision Problems via Filtering (ICCV 2019 · similarity 0.86)
- Improving Progressive Generation with Decomposable Flow Matching (NeurIPS 2025 · similarity 0.86)
- Balancing Frequencies and Pixels in Flow Matching (NeurIPS 2026 · similarity 0.85)
- Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching (NeurIPS 2024 · similarity 0.84)
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.
