NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
- MDE
Main:8 Pages
7 Figures
Bibliography:7 Pages
4 Tables
Abstract
This paper reports on the NTIRE 2025 challenge on HR Depth From images of Specular and Transparent surfaces, held in conjunction with the New Trends in Image Restoration and Enhancement (NTIRE) workshop at CVPR 2025. This challenge aims to advance the research on depth estimation, specifically to address two of the main open issues in the field: high-resolution and non-Lambertian surfaces. The challenge proposes two tracks on stereo and single-image depth estimation, attracting about 177 registered participants. In the final testing stage, 4 and 4 participating teams submitted their models and fact sheets for the two tracks.
View on arXiv@article{ramirez2025_2506.05815,
title={ NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces },
author={ Pierluigi Zama Ramirez and Fabio Tosi and Luigi Di Stefano and Radu Timofte and Alex Costanzino and Matteo Poggi and Samuele Salti and Stefano Mattoccia and Zhe Zhang and Yang Yang and Wu Chen and Anlong Ming and Mingshuai Zhao and Mengying Yu and Shida Gao and Xiangfeng Wang and Feng Xue and Jun Shi and Yong Yang and Yong A and Yixiang Jin and Dingzhe Li and Aryan Shukla and Liam Frija-Altarac and Matthew Toews and Hui Geng and Tianjiao Wan and Zijian Gao and Qisheng Xu and Kele Xu and Zijian Zang and Jameer Babu Pinjari and Kuldeep Purohit and Mykola Lavreniuk and Jing Cao and Shenyi Li and Kui Jiang and Junjun Jiang and Yong Huang },
journal={arXiv preprint arXiv:2506.05815},
year={ 2025 }
}Comments on this paper