Pith. sign in

REVIEW 3 cited by

SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.14793 v1 pith:DKKMAM2O submitted 2024-05-23 cs.CV

Yihan Wang , Lahav Lipson , Jia Deng This is my paper · ORCID
classification cs.CV
keywords sea-raftflowraftaccuratebestefficientfastergeneralization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce SEA-RAFT, a more simple, efficient, and accurate RAFT for optical flow. Compared with RAFT, SEA-RAFT is trained with a new loss (mixture of Laplace). It directly regresses an initial flow for faster convergence in iterative refinements and introduces rigid-motion pre-training to improve generalization. SEA-RAFT achieves state-of-the-art accuracy on the Spring benchmark with a 3.69 endpoint-error (EPE) and a 0.36 1-pixel outlier rate (1px), representing 22.9% and 17.8% error reduction from best published results. In addition, SEA-RAFT obtains the best cross-dataset generalization on KITTI and Spring. With its high efficiency, SEA-RAFT operates at least 2.3x faster than existing methods while maintaining competitive performance. The code is publicly available at https://github.com/princeton-vl/SEA-RAFT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MegaFlow: Zero-Shot Large Displacement Optical Flow

    cs.CV 2026-03 accept novelty 6.0 of 10

    MegaFlow reaches SOTA zero-shot optical flow (especially large motions) and competitive point tracking by global matching of pre-trained ViT features followed by lightweight multi-frame refinement.

  2. Discovering and using Spelke segments

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SpelkeNet, a self-supervised video world model, discovers Spelke segments in static images by aggregating motion correlations across imagined pokes.

  3. Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A single-image-to-3D pipeline that renders realistic image pairs and flow labels at scale, training optical flow models to outperform synthetic-data and unsupervised baselines on KITTI.

Pith tools