NITRE 2024 Challenge on HR Depth from Images of Specular and Transparent Surfaces.

Aishi Huang

Abstract: This paper reports on the NTIRE 2024 challenge on HR Depth From images of Specular and Transparent surfaces, held in conjunction with the New Trends in Image Restora- tion and Enhancement (NTIRE) workshop at CVPR 2024. This challenge aims to advance the research on depth es- timation, specifically to address two of the main open is- sues in the field: high-resolution and non-Lambertian sur- faces. The challenge proposes two tracks on stereo and single-image depth estimation, attracting about 120 regis- tered participants. In the final testing stage, 2 and 8 partic- ipating teams submitted their models and fact sheets for the two tracks.