The 'NTIRE 2024 Transparent Surface Challenge' dataset is part of the "NTIRE 2024: HR Depth from Images of Specular and Transparent Surfaces Challenge," held with the New Trends in Image Restoration and Enhancement (NTIRE) workshop at CVPR 2024. The challenge targets advancing depth estimation in challenging scenarios, specifically high-resolution images of specular and transparent (non-Lambertian) surfaces. The affiliated dataset, referred to as the 'Booster' dataset, provides annotated images focusing on these types of surfaces to foster algorithms capable of accurate, high-resolution depth prediction in difficult visual conditions. The dataset supports both monocular and stereo depth estimation tracks and is intended to catalyze the field toward solving unsolved challenges in depth prediction.
No results indexed yet — be the first to submit a score.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.