Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors

TL;DR

This paper introduces a real-time inpainting method that fuses sparse depth maps with single-view depth predictions using a CNN-parameterized CRF, effectively generating dense depth maps from various sparse sources.

Contribution

It proposes a novel data fusion approach with confidence weights predicted by CNNs, enabling flexible, real-time inpainting of sparse depth maps from different sensors and scales.

Findings

Effective real-time inpainting demonstrated on various sensor data.

Robust fusion reduces impact of outliers in depth maps.

Flexible application to indoor and outdoor scenes.

Abstract

We present ``just-in-time reconstruction" as real-time image-guided inpainting of a map with arbitrary scale and sparsity to generate a fully dense depth map for the image. In particular, our goal is to inpaint a sparse map --- obtained from either a monocular visual SLAM system or a sparse sensor --- using a single-view depth prediction network as a virtual depth sensor. We adopt a fairly standard approach to data fusion, to produce a fused depth map by performing inference over a novel fully-connected Conditional Random Field (CRF) which is parameterized by the input depth maps and their pixel-wise confidence weights. Crucially, we obtain the confidence weights that parameterize the CRF model in a data-dependent manner via Convolutional Neural Networks (CNNs) which are trained to model the conditional depth error distributions given each source of input depth map and the associated RGB image. Our CRF model penalises absolute depth error in its nodes and pairwise scale-invariant depth error in its edges, and the confidence-based fusion minimizes the impact of outlier input depth values on the fused result. We demonstrate the flexibility of our method by real-time inpainting of ORB-SLAM, Kinect, and LIDAR depth maps acquired both indoors and outdoors at arbitrary scale and varied amount of irregular sparsity.