Dynamic to Static Lidar Scan Reconstruction Using Adversarially Trained Auto Encoder

Authors

  • Prashant Kumar Indian Institute of Science, Bangalore, India
  • Sabyasachi Sahoo Indian Institute of Science, Bangalore, India
  • Vanshil Shah Indian Institute of Science, Bangalore, India
  • Vineetha Kondameedi Indian Institute of Science, Bangalore, India
  • Abhinav Jain Indian Institute of Science, Bangalore, India
  • Akshaj Verma Indian Institute of Science, Bangalore, India
  • Chiranjib Bhattacharyya Indian Institute of Science, Bangalore, India
  • Vinay Vishwanath AMIDC Pvt Ltd, Bangalore, India Chennai Mathematical Institute, Chennai, India

Keywords:

3D Computer Vision, Vision for Robotics & Autonomous Driving

Abstract

Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been recently explored for visual SLAM, but to the best of our knowledge no work has been attempted to address DST for LiDAR scans. The problem is of critical importance due to wide-spread adoption of LiDAR in Autonomous Vehicles. We show that state-of the art methods developed for the visual domain when adapted for LiDAR scans perform poorly. We develop DSLR, a deep generative model which learns a mapping between dynamic scan to its static counterpart through an adversarially trained autoencoder. Our model yields the first solution for DST on LiDAR that generates static scans without using explicit segmentation labels. DSLR cannot always be applied to real world data due to lack of paired dynamic-static scans. Using Unsupervised Domain Adaptation, we propose DSLR-UDA for transfer to real world data and experimentally show that this performs well in real world settings. Additionally, if segmentation information is available, we extend DSLR to DSLR-Seg to further improve the reconstruction quality. DSLR gives the state of the art performance on simulated and real-world datasets and also shows at least 4× improvement. We show that DSLR, unlike the existing baselines, is a practically viable model with its reconstruction quality within the tolerable limits for tasks pertaining to autonomous navigation like SLAM in dynamic environments.

Downloads

Published

2021-05-18

How to Cite

Kumar, P., Sahoo, S., Shah, V., Kondameedi, V., Jain, A., Verma, A., Bhattacharyya, C., & Vishwanath, V. (2021). Dynamic to Static Lidar Scan Reconstruction Using Adversarially Trained Auto Encoder. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 1836-1844. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16278

Issue

Section

AAAI Technical Track on Computer Vision II