Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data
Open Access
- 16 December 2022
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (3) , 796-812
Abstract
Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground-truth annotations for depth completion settings can be difficult and, at the same time, a significant domain gap between real LiDAR measurements and synthetic data has prevented from successful training of models in virtual settings. We propose a domain adaptation approach for sparse-to-dense depth completion that is trained from synthetic data, without annotations in the real domain or additional sensors. Our approach simulates the real sensor noise in an RGB + LiDAR set-up, and consists of three modules: simulating the real LiDAR input in the synthetic domain via projections, filtering the real noisy LiDAR for supervision and adapting the synthetic RGB image using a CycleGAN approach. We extensively evaluate these modules in the KITTI depth completion benchmark.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/S032398/1)
This publication has 71 references indexed in Scilit:
- The Fast Bilateral Solver2016
- A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM2014
- Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation2013
- Review of stereo vision algorithms and their suitability for resource-limited systemsJournal of Real-Time Image Processing, 2013
- Indoor Segmentation and Support Inference from RGBD Images2012
- Review of Stereo Vision Algorithms: From Software to HardwareInternational Journal of Optomechatronics, 2008
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Motion and Structure from Feature Correspondences: A Review2002
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002
- MOTION AND STRUCTURE FROM MOTION IN A PIECEWISE PLANAR ENVIRONMENTInternational Journal of Pattern Recognition and Artificial Intelligence, 1988