Nonlinear Motion-Guided and Spatio-Temporal Aware Network for Unsupervised Event-Based Optical Flow

• URL: http://arxiv.org/abs/2505.05089v1
• Date: Thu, 08 May 2025 09:39:19 GMT
• Title: Nonlinear Motion-Guided and Spatio-Temporal Aware Network for Unsupervised Event-Based Optical Flow
• Authors: Zuntao Liu, Hao Zhuang, Junjie Jiang, Yuhang Song, Zheng Fang,
• Abstract summary: Event-based optical flow estimation has potential to capture continuous motion information over time and space.<n>Most existing learning-based methods for event-based optical flow adopt frame-based techniques.<n>We propose a novel unsupervised event-based optical flow network focusing on long-time sequences.<n>Our method ranks first among unsupervised learning methods on the MVSEC and DSECFlow datasets.
• Score: 8.16793106376875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Event cameras have the potential to capture continuous motion information over time and space, making them well-suited for optical flow estimation. However, most existing learning-based methods for event-based optical flow adopt frame-based techniques, ignoring the spatio-temporal characteristics of events. Additionally, these methods assume linear motion between consecutive events within the loss time window, which increases optical flow errors in long-time sequences. In this work, we observe that rich spatio-temporal information and accurate nonlinear motion between events are crucial for event-based optical flow estimation. Therefore, we propose E-NMSTFlow, a novel unsupervised event-based optical flow network focusing on long-time sequences. We propose a Spatio-Temporal Motion Feature Aware (STMFA) module and an Adaptive Motion Feature Enhancement (AMFE) module, both of which utilize rich spatio-temporal information to learn spatio-temporal data associations. Meanwhile, we propose a nonlinear motion compensation loss that utilizes the accurate nonlinear motion between events to improve the unsupervised learning of our network. Extensive experiments demonstrate the effectiveness and superiority of our method. Remarkably, our method ranks first among unsupervised learning methods on the MVSEC and DSEC-Flow datasets. Our project page is available at https://wynelio.github.io/E-NMSTFlow.

Related papers

• TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion [18.191333256398845]
  A hurdle for event-based video frame (VFI) is how to deal with non-linear motion.<n>We propose a novel continuous point tracking-based VFI framework, named TimeTracker.<n>Our method outperforms prior arts in both motion estimation and frame quality.
  arXiv  Detail & Related papers  (2025-05-06T02:12:19Z)
• SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining [62.433137130087445]
  SuperFlow++ is a novel framework that integrates pretraining and downstream tasks using consecutive camera pairs.<n>We show that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions.<n>With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving.
  arXiv  Detail & Related papers  (2025-03-25T17:59:57Z)
• Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation [47.75348821902489]
  Current optical flow methods exploit the stable appearance of frame (or RGB) data to establish robust correspondences across time.<n>Event cameras, on the other hand, provide high-temporal-resolution motion cues and excel in challenging scenarios.<n>This study introduces a novel approach that uses a spatially dense modality to guide the aggregation of the temporally dense event modality.
  arXiv  Detail & Related papers  (2025-01-01T13:40:09Z)
• Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation [34.529280562470746]
  We introduce a novel self-supervised loss combining the Contrast Maximization framework with a non-linear motion prior in the form of pixel-level trajectories. Their effectiveness is demonstrated in two scenarios: In dense continuous-time motion estimation, our method improves the zero-shot performance of a synthetically trained model by 29%.
  arXiv  Detail & Related papers  (2024-07-15T15:18:28Z)
• GAFlow: Incorporating Gaussian Attention into Optical Flow [62.646389181507764]
  We push Gaussian Attention (GA) into the optical flow models to accentuate local properties during representation learning. We introduce a novel Gaussian-Constrained Layer (GCL) which can be easily plugged into existing Transformer blocks. For reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM)
  arXiv  Detail & Related papers  (2023-09-28T07:46:01Z)
• AccFlow: Backward Accumulation for Long-Range Optical Flow [70.4251045372285]
  This paper proposes a novel recurrent framework called AccFlow for long-range optical flow estimation. We demonstrate the superiority of backward accumulation over conventional forward accumulation. Experiments validate the effectiveness of AccFlow in handling long-range optical flow estimation.
  arXiv  Detail & Related papers  (2023-08-25T01:51:26Z)
• Towards Anytime Optical Flow Estimation with Event Cameras [35.685866753715416]
  Event cameras are capable of responding to log-brightness changes in microseconds. Existing datasets collected via event cameras provide limited frame rate optical flow ground truth. We propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow.
  arXiv  Detail & Related papers  (2023-07-11T06:15:12Z)
• TMA: Temporal Motion Aggregation for Event-based Optical Flow [27.49029251605363]
  Event cameras have the ability to record continuous and detailed trajectories of objects with high temporal resolution. Most existing learning-based approaches for event optical flow estimation ignore the inherent temporal continuity of event data. We propose a novel Temporal Motion Aggregation (TMA) approach to unlock its potential.
  arXiv  Detail & Related papers  (2023-03-21T06:51:31Z)
• Motion-inductive Self-supervised Object Discovery in Videos [99.35664705038728]
  We propose a model for processing consecutive RGB frames, and infer the optical flow between any pair of frames using a layered representation. We demonstrate superior performance over previous state-of-the-art methods on three public video segmentation datasets.
  arXiv  Detail & Related papers  (2022-10-01T08:38:28Z)
• Dense Continuous-Time Optical Flow from Events and Frames [27.1850072968441]
  We show that it is possible to compute per-pixel, continuous-time optical flow using events from an event camera. We leverage these benefits to predict pixel trajectories densely in continuous time via parameterized B'ezier curves. Our model is the first method that can regress dense pixel trajectories from event data.
  arXiv  Detail & Related papers  (2022-03-25T14:29:41Z)
• EM-driven unsupervised learning for efficient motion segmentation [3.5232234532568376]
  This paper presents a CNN-based fully unsupervised method for motion segmentation from optical flow. We use the Expectation-Maximization (EM) framework to leverage the loss function and the training procedure of our motion segmentation neural network. Our method outperforms comparable unsupervised methods and is very efficient.
  arXiv  Detail & Related papers  (2022-01-06T14:35:45Z)
• SCFlow: Optical Flow Estimation for Spiking Camera [50.770803466875364]
  Spiking camera has enormous potential in real applications, especially for motion estimation in high-speed scenes. Optical flow estimation has achieved remarkable success in image-based and event-based vision, but % existing methods cannot be directly applied in spike stream from spiking camera. This paper presents, SCFlow, a novel deep learning pipeline for optical flow estimation for spiking camera.
  arXiv  Detail & Related papers  (2021-10-08T06:16:45Z)
• Unsupervised Motion Representation Enhanced Network for Action Recognition [4.42249337449125]
  Motion representation between consecutive frames has proven to have great promotion to video understanding. TV-L1 method, an effective optical flow solver, is time-consuming and expensive in storage for caching the extracted optical flow. We propose UF-TSN, a novel end-to-end action recognition approach enhanced with an embedded lightweight unsupervised optical flow estimator.
  arXiv  Detail & Related papers  (2021-03-05T04:14:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.