NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces

Pierluigi Zama Ramirez; Fabio Tosi; Luigi Di Stefano; Radu Timofte; Alex Costanzino; Matteo Poggi; Samuele Salti; Stefano Mattoccia; Zhe Zhang; Yang Yang; Wu Chen; Anlong Ming; Mingshuai Zhao; Mengying Yu; Shida Gao; Xiangfeng Wang; Feng Xue; Jun Shi; Yong Yang; A. Yong; Yixiang Jin; Dingzhe Li; Aryan Shukla; Liam Frija-Altarac; Matthew Toews; Hui Geng; Tianjiao Wan; Zijian Gao; Qisheng Xu; Kele Xu; Zijian Zang; Jameer Babu Pinjari; Kuldeep Purohit; Mykola Lavreniuk; Jing Cao; Shenyi Li; Kui Jiang; Junjun Jiang; Y. Huang

doi:10.1109/CVPRW67362.2025.00098

NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces

Pierluigi Zama Ramirez^*
, Fabio Tosi
, Luigi Di Stefano
, Radu Timofte
, Alex Costanzino
, Matteo Poggi
, Samuele Salti
, Stefano Mattoccia
, Zhe Zhang
, Yang Yang
, Wu Chen
, Anlong Ming
, Mingshuai Zhao
, Mengying Yu
, Shida Gao
, Xiangfeng Wang
, Feng Xue
, Jun Shi
, Yong Yang
, A. Yong

Yixiang Jin, Dingzhe Li, Aryan Shukla, Liam Frija-Altarac, Matthew Toews, Hui Geng, Tianjiao Wan, Zijian Gao, Qisheng Xu, Kele Xu, Zijian Zang, Jameer Babu Pinjari, Kuldeep Purohit, Mykola Lavreniuk, Jing Cao, Shenyi Li, Kui Jiang, Junjun Jiang, Y. Huang

^*Corresponding author for this work

Faculty of Computing

University of Bologna
University of Würzburg
Beijing University of Posts and Telecommunications
University of Trento
Samsung RD Institute China-Beijing (SRC-Beijing)
École de technologie supérieure
National University of Defense Technology
Fudan University
National Academy of Sciences of Ukraine
Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

28 Scopus citations

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.

Original language	English
Title of host publication	Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Publisher	IEEE Computer Society
Pages	978-992
Number of pages	15
ISBN (Electronic)	9798331599942
DOIs	https://doi.org/10.1109/CVPRW67362.2025.00098
State	Published - 2025
Event	2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 - Nashville, United States Duration: 11 Jun 2025 → 12 Jun 2025

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Country/Territory	United States
City	Nashville
Period	11/06/25 → 12/06/25

Keywords

challenge
depth
mono
stereo
transparent

Access to Document

10.1109/CVPRW67362.2025.00098

Cite this

Ramirez, P. Z., Tosi, F., Di Stefano, L., Timofte, R., Costanzino, A., Poggi, M., Salti, S., Mattoccia, S., Zhang, Z., Yang, Y., Chen, W., Ming, A., Zhao, M., Yu, M., Gao, S., Wang, X., Xue, F., Shi, J., Yang, Y., ... Huang, Y. (2025). NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 (pp. 978-992). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW67362.2025.00098

Ramirez, Pierluigi Zama ; Tosi, Fabio ; Di Stefano, Luigi et al. / NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces. Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society, 2025. pp. 978-992 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

@inproceedings{5f83b2e9503c4f6697f1a52af6d5546d,

title = "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.",

keywords = "challenge, depth, mono, stereo, transparent",

author = "Ramirez, \{Pierluigi Zama\} and Fabio Tosi and \{Di Stefano\}, Luigi 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 A. Yong 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 Pinjari, \{Jameer Babu\} and Kuldeep Purohit and Mykola Lavreniuk and Jing Cao and Shenyi Li and Kui Jiang and Junjun Jiang and Y. Huang",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 ; Conference date: 11-06-2025 Through 12-06-2025",

year = "2025",

doi = "10.1109/CVPRW67362.2025.00098",

language = "英语",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "978--992",

booktitle = "Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025",

address = "美国",

}

Ramirez, PZ, Tosi, F, Di Stefano, L, Timofte, R, Costanzino, A, Poggi, M, Salti, S, Mattoccia, S, Zhang, Z, Yang, Y, Chen, W, Ming, A, Zhao, M, Yu, M, Gao, S, Wang, X, Xue, F, Shi, J, Yang, Y, Yong, A, Jin, Y, Li, D, Shukla, A, Frija-Altarac, L, Toews, M, Geng, H, Wan, T, Gao, Z, Xu, Q, Xu, K, Zang, Z, Pinjari, JB, Purohit, K, Lavreniuk, M, Cao, J, Li, S, Jiang, K , Jiang, J & Huang, Y 2025, NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces. in Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 978-992, 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025, Nashville, United States, 11/06/25. https://doi.org/10.1109/CVPRW67362.2025.00098

NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces. / Ramirez, Pierluigi Zama; Tosi, Fabio; Di Stefano, Luigi et al.
Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society, 2025. p. 978-992 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces

AU - Ramirez, Pierluigi Zama

AU - Tosi, Fabio

AU - Di Stefano, Luigi

AU - Timofte, Radu

AU - Costanzino, Alex

AU - Poggi, Matteo

AU - Salti, Samuele

AU - Mattoccia, Stefano

AU - Zhang, Zhe

AU - Yang, Yang

AU - Chen, Wu

AU - Ming, Anlong

AU - Zhao, Mingshuai

AU - Yu, Mengying

AU - Gao, Shida

AU - Wang, Xiangfeng

AU - Xue, Feng

AU - Shi, Jun

AU - Yang, Yong

AU - Yong, A.

AU - Jin, Yixiang

AU - Li, Dingzhe

AU - Shukla, Aryan

AU - Frija-Altarac, Liam

AU - Toews, Matthew

AU - Geng, Hui

AU - Wan, Tianjiao

AU - Gao, Zijian

AU - Xu, Qisheng

AU - Xu, Kele

AU - Zang, Zijian

AU - Pinjari, Jameer Babu

AU - Purohit, Kuldeep

AU - Lavreniuk, Mykola

AU - Cao, Jing

AU - Li, Shenyi

AU - Jiang, Kui

AU - Jiang, Junjun

AU - Huang, Y.

PY - 2025

Y1 - 2025

N2 - 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.

AB - 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.

KW - challenge

KW - depth

KW - mono

KW - stereo

KW - transparent

UR - https://www.scopus.com/pages/publications/105017862661

U2 - 10.1109/CVPRW67362.2025.00098

DO - 10.1109/CVPRW67362.2025.00098

M3 - 会议稿件

AN - SCOPUS:105017862661

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 978

EP - 992

BT - Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025

PB - IEEE Computer Society

T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025

Y2 - 11 June 2025 through 12 June 2025

ER -

Ramirez PZ, Tosi F, Di Stefano L, Timofte R, Costanzino A, Poggi M et al. NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society. 2025. p. 978-992. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW67362.2025.00098

NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this