-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ramirez_2025_CVPR, author = {Ramirez, Pierluigi Zama and Tosi, Fabio and Di Stefano, Luigi and Timofte, Radu and Costanzino, Alex and Poggi, Matteo and Salti, Samuele and Mattoccia, Stefano and Zhang, Zhe and Yang, Yang and Chen, Wu and Ming, Anlong and Zhao, Mingshuai and Yu, Mengying and Gao, Shida and Wang, Xiangfeng and Xue, Feng and Shi, Jun and Yang, Yong and A, Yong and Jin, Yixiang and Li, Dingzhe and Shukla, Aryan and Frija-Altarac, Liam and Toews, Matthew and Geng, Hui and Wan, Tianjiao and Gao, Zijian and Xu, Qisheng and Xu, Kele and Zang, Zijian and Babu, Jameer and Purohit, Kuldeep and Lavreniuk, Mykola and Cao, Jing and Li, Shenyi and Jiang, Kui and Jiang, Junjun and Huang, Yong}, title = {NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {987-1001} }
NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
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.
Related Material