DeepAI AI Chat
Log In Sign Up

Robust Depth Completion with Uncertainty-Driven Loss Functions

by   Yufan Zhu, et al.
West Virginia University
Xidian University
NetEase, Inc

Recovering a dense depth image from sparse LiDAR scans is a challenging task. Despite the popularity of color-guided methods for sparse-to-dense depth completion, they treated pixels equally during optimization, ignoring the uneven distribution characteristics in the sparse depth map and the accumulated outliers in the synthesized ground truth. In this work, we introduce uncertainty-driven loss functions to improve the robustness of depth completion and handle the uncertainty in depth completion. Specifically, we propose an explicit uncertainty formulation for robust depth completion with Jeffrey's prior. A parametric uncertain-driven loss is introduced and translated to new loss functions that are robust to noisy or missing data. Meanwhile, we propose a multiscale joint prediction model that can simultaneously predict depth and uncertainty maps. The estimated uncertainty map is also used to perform adaptive prediction on the pixels with high uncertainty, leading to a residual map for refining the completion results. Our method has been tested on KITTI Depth Completion Benchmark and achieved the state-of-the-art robustness performance in terms of MAE, IMAE, and IRMSE metrics.


page 1

page 2

page 3

page 4

page 5

page 6


DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network

Depth Completion can produce a dense depth map from a sparse input and p...

Depth Coefficients for Depth Completion

Depth completion involves estimating a dense depth image from sparse dep...

SGTBN: Generating Dense Depth Maps from Single-Line LiDAR

Depth completion aims to generate a dense depth map from the sparse dept...

Least Square Estimation Network for Depth Completion

Depth completion is a fundamental task in computer vision and robotics r...

Bayesian Deep Basis Fitting for Depth Completion with Uncertainty

In this work we investigate the problem of uncertainty estimation for im...

Learning Joint 2D-3D Representations for Depth Completion

In this paper, we tackle the problem of depth completion from RGBD data....

Towards Domain-agnostic Depth Completion

Existing depth completion methods are often targeted at a specific spars...