TY - GEN
T1 - Thermal Image Super-Resolution Challenge Results - PBVS 2025
AU - TISR 2025 organization team, 3 authors, including
AU - Rivadeneira, Rafael E.
AU - Sappa, Angel D.
AU - Hammoud, Riad
AU - Top Participant Teams, 17 authors, including
AU - Ko, Donggeun
AU - Kwak, Youngsang
AU - Kwak, Jaehwa
AU - Zhong, Zhiwei
AU - Li, Yung-Hui
AU - Wang, Shiqi
AU - De Kerf, Thomas
AU - Evans, Rhys
AU - Shen, Qiangqiang
AU - Wang, Hanzhang
AU - Zhang, Xuanqi
AU - Zhong, Hang
AU - Wang, Yu
AU - Zhao, Shengjie
AU - Rao, Jiyong
AU - Puttagunta, Raghunath Sai
AU - Li, Zhu
PY - 2025
Y1 - 2025
N2 - This paper presents the results of the Sixth Thermal Image Super-Resolution Challenge held within the Perception Beyond the Visible Spectrum (PBVS) workshop at CVPR 2025. The challenge maintains the same cross-spectral benchmark dataset as the previous year, consisting of 1000 thermal images each paired with corresponding high-resolution RGB images. Track 1 focuses on single thermal image super-resolution, enhancing low-resolution infrared images by a factor of x 8, whereas Track 2 addresses guided thermal image super-resolution, performing super-resolution at scale factors of x 8 and x 16 by leveraging high-resolution RGB images as auxiliary inputs. The 2025 edition attracted increased participation, with 128 teams competing in Track 1 and 86 teams in Track 2. The paper describes methodologies employed by the top participating teams, emphasizing innovations in transformer-based and hybrid architectures, and provides a detailed comparative analysis of the results between the 2024 and 2025 challenges. This analysis reveals significant progress in thermal image reconstruction accuracy, showcasing notable advances achieved by the leading methodologies. © 2025 IEEE.
AB - This paper presents the results of the Sixth Thermal Image Super-Resolution Challenge held within the Perception Beyond the Visible Spectrum (PBVS) workshop at CVPR 2025. The challenge maintains the same cross-spectral benchmark dataset as the previous year, consisting of 1000 thermal images each paired with corresponding high-resolution RGB images. Track 1 focuses on single thermal image super-resolution, enhancing low-resolution infrared images by a factor of x 8, whereas Track 2 addresses guided thermal image super-resolution, performing super-resolution at scale factors of x 8 and x 16 by leveraging high-resolution RGB images as auxiliary inputs. The 2025 edition attracted increased participation, with 128 teams competing in Track 1 and 86 teams in Track 2. The paper describes methodologies employed by the top participating teams, emphasizing innovations in transformer-based and hybrid architectures, and provides a detailed comparative analysis of the results between the 2024 and 2025 challenges. This analysis reveals significant progress in thermal image reconstruction accuracy, showcasing notable advances achieved by the leading methodologies. © 2025 IEEE.
KW - challenge
KW - dataset
KW - super-resolution
KW - thermal images
UR - http://www.scopus.com/inward/record.url?scp=105017855332&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105017855332&origin=recordpage
U2 - 10.1109/CVPRW67362.2025.00448
DO - 10.1109/CVPRW67362.2025.00448
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 979-8-3315-9995-9
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 4621
EP - 4630
BT - Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
PB - IEEE
T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2025)
Y2 - 11 June 2025 through 15 June 2025
ER -