NTIRE 2023 Challenge on HR Depth from Images of Specular and Transparent Surfaces

This paper reports about the NTIRE 2023 challenge on HR Depth From images of Specular and Transparent surfaces, held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2023. This challenge is held to boost the research on depth estimation, mainly to deal with two of the open issues in the field: high-resolution images and non-Lambertian surfaces characterizing specular and transparent materials. The challenge is divided into two tracks: a stereo track focusing on disparity estimation from rectified pairs and a mono track dealing with single-image depth estimation. The challenge attracted about 100 registered participants for the two tracks. In the final testing stage, 5 participating teams submitted their models and fact sheets, 2 and 3 for the Stereo and Mono tracks, respectively.

1. Introduction

Since the advent of computer vision, estimating depth from images has always been the object of study for a large part of the research community. Indeed, recovering depth represents the first pivotal step to pave the way to several downstream applications, ranging from augmented reality, robotics, autonomous navigation, and more. Depth can be measured either by means of dedicated, active sensors – LiDARs, ToFs, Radars, etc. – or through standard imaging sensors by developing algorithms / deep neural networks. Although depth sensing technologies grew fast in the last decade and proved a mature reality, some challenges still preclude their unbound deployment.