Pith. sign in

REVIEW 4 cited by

Towards Anytime Optical Flow Estimation with Event Cameras

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 2307.05033 v3 pith:54FLQBPP submitted 2023-07-11 cs.CV cs.ROeess.IV

Yaozu Ye , Hao Shi , Kailun Yang , Ze Wang , Xiaoting Yin , Lei Sun , Yaonan Wang , Kaiwei Wang This is my paper · ORCID
classification cs.CVcs.ROeess.IV
keywords flowopticaleventestimationcameraseva-flowanytimeground
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Event cameras respond to changes in log-brightness at the millisecond level, making them ideal for optical flow estimation. However, existing datasets from event cameras provide only low frame rate ground truth for optical flow, limiting the research potential of event-driven optical flow. To address this challenge, we introduce a low-latency event representation, Unified Voxel Grid, and propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. Furthermore, we propose the Rectified Flow Warp Loss (RFWL) for the unsupervised assessment of intermediate optical flow. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Event-aided Semantic Scene Completion

    cs.CV 2025-02 conditional novelty 7.0 of 10

    Fusing event-camera data during the 2D-to-3D lifting step improves semantic scene completion accuracy and robustness on a new real-world benchmark and on corrupted SemanticKITTI.

  2. Learning Normal Flow Directly From Event Neighborhoods

    cs.CV 2024-12 reject novelty 6.0 of 10

    A point-based network learns per-event normal flow from raw event camera data and, with IMU data, estimates egomotion; it transfers across datasets better than frame-based optical flow methods.

  3. Labits: Layered Bidirectional Time Surfaces Representation for Event Camera-based Continuous Dense Trajectory Estimation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A layered bidirectional time-surface representation plus a local-flow feature extractor reduces dense trajectory end-point error by 49% on the MultiFlow event-camera benchmark.

  4. Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues

    cs.CV 2026-08 conditional novelty 5.0 of 10

    Harris eigenvalues and spatiotemporal density values from event cameras encode motion direction and, when added to an optical flow network, improve accuracy in data-scarce settings.

Pith tools