DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance

Abstract

Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution. Accurate depth sensors such as LiDARs are often heavy, expensive and can only provide sparse depth while lighter depth sensors such as stereo cameras are noiser in comparison. We propose an end-to-end learning algorithm that is capable of using sparse, noisy input depth for refinement and depth completion. Our model also produces the camera pose as a byproduct, making it a great solution for autonomous systems. We evaluate our approach on both indoor and outdoor datasets. Empirical results show that our method performs well on the KITTI~\cite{kitti_geiger2012we} dataset when compared to other competing methods, while having superior performance in dealing with sparse, noisy input depth on the TUM~\cite{sturm12iros} dataset.

References in corpus (6)

• SfM-Net: Learning of Structure and Motion from Video
• Confidence Propagation through CNNs for Guided Sparse Depth Regression
• Fast, Autonomous Flight in GPS-Denied and Cluttered Environments
• Direct Sparse Odometry
• Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras
• A Compromise Principle in Deep Monocular Depth Estimation

Cited by in corpus (4)

• On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation
• Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion
• Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications
• Towards Real-Time Monocular Depth Estimation for Robotics: A Survey