Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
Tracking and reconstructing 3D objects from cluttered scenes are the key components for computer vision, robotics and autonomous driving systems. While recent progress in implicit function has shown encouraging results on high-quality 3D shape reconstruction, it is still very challenging to generalize to cluttered and partially observable LiDAR data. In this paper, we propose to leverage the continuity in video data. We introduce a novel and unified framework which utilizes a neural implicit function to simultaneously track and reconstruct 3D objects in the wild. Our approach adapts the DeepSDF model (i.e., an instantiation of the implicit function) in the video online, iteratively improving the shape reconstruction while in return improving the tracking, and vice versa. We experiment with both Waymo and KITTI datasets and show significant improvements over state-of-the-art methods for both tracking and shape reconstruction tasks. Our project page is at https://jianglongye.com/implicit-tracking .
Code (1)
Tasks
3D Shape ReconstructionAutonomous DrivingObject TrackingSimilar Papers 제목 키워드 기반
Extended Object Tracking and Classification based on Linear Splines
This paper introduces a framework based on linear splines for 2-dimensional extended object tracking and classification. Unlike state of the art models, linear splines allow to represent extended objects whose contour is…
ObjectObject TrackingTRIC-track: Tracking by Regression With Incrementally Learned Cascades
This paper proposes a novel approach to part-based tracking by replacing local matching of an appearance model by direct prediction of the displacement between local image patches and part locations. We propose to use ca…
Incremental LearningregressionRecursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. Th…
Continual LearningFew-Shot LearningMeta-LearningOne-Shot Learning+1Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with distractors, occlusion, and nonlinear m…
Visual Object TrackingThree-Dimensional Extended Object Tracking and Shape Learning Using Gaussian Processes
In this study, we investigate the problem of tracking objects with unknown shapes using three-dimensional (3D) point cloud data. We propose a Gaussian process-based model to jointly estimate object kinematics, including …
Gaussian ProcessesObjectObject Tracking