FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc. Conventionally, scene flow is estimated from dense/regular RGB video frames. With the development of depth-sensing technologies, precise 3D measurements are available via point clouds which have sparked new research in 3D scene flow. Nevertheless, it remains challenging to extract scene flow from point clouds due to the sparsity and irregularity in typical point cloud sampling patterns. One major issue related to irregular sampling is identified as the randomness during point set abstraction/feature extraction -- an elementary process in many flow estimation scenarios. A novel Spatial Abstraction with Attention (SA^2) layer is accordingly proposed to alleviate the unstable abstraction problem. Moreover, a Temporal Abstraction with Attention (TA^2) layer is proposed to rectify attention in temporal domain, leading to benefits with motions scaled in a larger range. Extensive analysis and experiments verified the motivation and significant performance gains of our method, dubbed as Flow Estimation via Spatial-Temporal Attention (FESTA), when compared to several state-of-the-art benchmarks of scene flow estimation.
Code (1)
Tasks
Autonomous DrivingRobot NavigationScene Flow EstimationSimilar Papers 제목 키워드 기반
EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching
Event cameras have shown promise in vision applications like optical flow estimation and stereo matching, with many specialized architectures leveraging the asynchronous and sparse nature of event data. However, existing…
Depth EstimationDisparity EstimationEvent-based Optical FlowOptical Flow Estimation+2Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Prediction
As a core technology of Intelligent Transportation System (ITS), traffic flow prediction has a wide range of applications. Traffic flow data are spatial-temporal, which are not only correlated to spatial locations in roa…
Incremental LearningKnowledge DistillationPredictionInterpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
Crowd flow prediction has been increasingly investigated in intelligent urban computing field as a fundamental component of urban management system. The most challenging part of predicting crowd flow is to measure the co…
ManagementPredictionTransFlow: Transformer as Flow Learner
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer…
Motion Estimationobject-detectionObject DetectionObject Tracking+3An effective spatial-temporal attention based neural network for traffic flow prediction
Due to its importance in Intelligent Transport Systems (ITS), traffic flow prediction has been the focus of many studies in the last few decades. Existing traffic flow prediction models mainly extract static spatial-te…
Prediction