Depth Completion via Deep Basis Fitting

Abstract

In this paper we consider the task of image-guided depth completion where our system must infer the depth at every pixel of an input image based on the image content and a sparse set of depth measurements. We propose a novel approach that builds upon the strengths of modern deep learning techniques and classical optimization algorithms and significantly improves performance. The proposed method replaces the final $1\times 1$ convolutional layer employed in most depth completion networks with a least squares fitting module which computes weights by fitting the implicit depth bases to the given sparse depth measurements. In addition, we show how our proposed method can be naturally extended to a multi-scale formulation for improved self-supervised training. We demonstrate through extensive experiments on various datasets that our approach achieves consistent improvements over state-of-the-art baseline methods with small computational overhead.

WACV2020

References in corpus (14)

• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• SfM-Net: Learning of Structure and Motion from Video
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• Virtual Worlds as Proxy for Multi-Object Tracking Analysis
• Training Deeper Convolutional Networks with Deep Supervision
• BA-Net: Dense Bundle Adjustment Network
• Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors
• Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera
• Differentiation of the Cholesky decomposition
• Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation
• DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image
• Dense Depth Posterior (DDP) from Single Image and Sparse Range
• Plug-and-Play: Improve Depth Estimation via Sparse Data Propagation
• Noise-Aware Unsupervised Deep Lidar-Stereo Fusion