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

TL;DR

This paper presents a unified online framework that leverages neural implicit functions to simultaneously track and reconstruct 3D objects in cluttered, real-world scenes, improving over existing methods.

Contribution

It introduces a novel method that adapts DeepSDF in real-time video data, enhancing both 3D shape reconstruction and object tracking in challenging environments.

Findings

Significant improvements over state-of-the-art on Waymo and KITTI datasets.

Effective online adaptation of implicit functions for dynamic scenes.

Enhanced accuracy in both object tracking and shape reconstruction.

Abstract

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 .