Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Jianglong, Chen, Yuntao, Wang, Naiyan, Wang, Xiaolong
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911831281369088
author Ye, Jianglong
Chen, Yuntao
Wang, Naiyan
Wang, Xiaolong
author_facet Ye, Jianglong
Chen, Yuntao
Wang, Naiyan
Wang, Xiaolong
contents 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 .
format Preprint
id arxiv_https___arxiv_org_abs_2111_12728
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
Ye, Jianglong
Chen, Yuntao
Wang, Naiyan
Wang, Xiaolong
Computer Vision and Pattern Recognition
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 .
title Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2111.12728