paper-with-me

Papers

Dense Continuous-Time Optical Flow from Events and Frames

2022-03-25 · Mathias Gehrig, Manasi Muglikar, Davide Scaramuzza

We present a method for estimating dense continuous-time optical flow from event data. Traditional dense optical flow methods compute the pixel displacement between two images. Due to missing information, these approaches cannot recover the pixel trajectories in the blind time between two images. In this work, we show that it is possible to compute per-pixel, continuous-time optical flow using events from an event camera. Events provide temporally fine-grained information about movement in pixel space due to their asynchronous nature and microsecond response time. We leverage these benefits to predict pixel trajectories densely in continuous time via parameterized B\'ezier curves. To achieve this, we build a neural network with strong inductive biases for this task: First, we build multiple sequential correlation volumes in time using event data. Second, we use B\'ezier curves to index these correlation volumes at multiple timestamps along the trajectory. Third, we use the retrieved correlation to update the B\'ezier curve representations iteratively. Our method can optionally include image pairs to boost performance further. To the best of our knowledge, our model is the first method that can regress dense pixel trajectories from event data. To train and evaluate our model, we introduce a synthetic dataset (MultiFlow) that features moving objects and ground truth trajectories for every pixel. Our quantitative experiments not only suggest that our method successfully predicts pixel trajectories in continuous time but also that it is competitive in the traditional two-view pixel displacement metric on MultiFlow and DSEC-Flow. Open source code and datasets are released to the public.

📄 PDF Abstract BibTeX arXiv:2203.13674

Code (1)

uzh-rpg/deep_ev_tracker pytorch

Tasks

Optical Flow Estimation

Similar Papers 제목 키워드 기반

Learning Dense and Continuous Optical Flow from an Event Camera

2022-11-16 · Zhexiong Wan, Yuchao Dai, Yuxin Mao

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the…

Optical Flow Estimation

TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion

2025-05-06 · CVPR 2025 1 · Haoyue Liu, Jinghan Xu, Yi Chang, Hanyu Zhou 외

Video frame interpolation (VFI) that leverages the bio-inspired event cameras as guidance has recently shown better performance and memory efficiency than the frame-based methods, thanks to the event cameras' advantages,…

Motion EstimationOptical Flow EstimationPoint TrackingVideo Frame Interpolation

Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation

2024-07-15 · Friedhelm Hamann, ZiYun Wang, Ioannis Asmanis, Kenneth Chaney 외

Current optical flow and point-tracking methods rely heavily on synthetic datasets. Event cameras are novel vision sensors with advantages in challenging visual conditions, but state-of-the-art frame-based methods cannot…

Motion EstimationOptical Flow EstimationPoint Tracking

From Contrast to Consistency: Rethinking Event-based Continuous-Time Optical Flow Estimation

2026-05-25 · Rui Hu, Song Wu, Wen Yang, Jinjian Wu arxiv

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, o…

Optical Flow Estimation

E-RAFT: Dense Optical Flow from Event Cameras

2021-08-24 · Mathias Gehrig, Mario Millhäusler, Daniel Gehrig, Davide Scaramuzza

We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely on matching costs computed from feature …

Feature CorrelationOptical Flow Estimation