-
[pdf]
[bibtex]@InProceedings{Vasluianu_2024_CVPR, author = {Vasluianu, Florin-Alexandru and Seizinger, Tim and Zhou, Zhuyun and Wu, Zongwei and Chen, Cailian and Timofte, Radu and Dong, Wei and Zhou, Han and Tian, Yuqiong and Chen, Jun and Fu, Xueyang and Lu, Xin and Zhu, Yurui and Wang, Xi and Li, Dong and Xiao, Jie and Zhang, Yunpeng and Zha, Zheng-Jun and Zhang, Zhao and Zhao, Suiyi and Wang, Bo and Luo, Yan and Wei, Yanyan and Zhao, Zhihao and Sun, Long and Yang, Tingting and Pan, Jinshan and Dong, Jiangxin and Tang, Jinhui and Benjdira, Bilel and Nassif, Mohammed and Koubaa, Anis and Elhayek, Ahmed and Ali, Anas M. and Tokoro, Kyotaro and Kawai, Kento and Yokoyama, Kaname and Seno, Takuya and Kondo, Yuki and Ukita, Norimichi and Li, Chenghua and Yang, Bo and Wu, Zhiqi and Chen, Gao and Yu, Yihan and Chen, Sixiang and Zhang, Kai and Ye, Tian and Zou, Wenbin and Lin, Yunlong and Xing, Zhaohu and Bai, Jinbin and Chai, Wenhao and Zhu, Lei and Maheshwari, Ritik and Verma, Rakshank and Tekchandani, Rahul and Hambarde, Praful and Tazi, Satya Narayan and Vipparthi, Santosh Kumar and Murala, Subrahmanyam and Lee, Jaeho and Kim, Seongwan and A, Sharif S M and Khujaev, Nodirkhuja and Tsoy, Roman and Gao, Fan and Yan, Weidan and Shao, Wenze and Zhang, Dengyin and Chen, Bin and Zhang, Siqi and Qian, Yanxin and Chen, Yuanbin and Zhou, Yuanbo and Tong, Tong and Wei, Rongfeng and Sun, Ruiqi and Liu, Yue and Akalwadi, Nikhil and Joshi, Amogh and Malagi, Sampada and Desai, Chaitra and Tabib, Ramesh Ashok and Mudenagudi, Uma and Murtaza, Ali and Khairuddin, Uswah and Faudzi, Ahmad Athif Mohd and Dukre, Adinath and Deshmukh, Vivek and Phutke, Shruti S. and Kulkarni, Ashutosh and Vipparthi, Santosh Kumar and Gonde, Anil and Murala, Subrahmanyam and K, Arun Karthik and N, Manasa and Priya, Shri Hari and Hao, Wei and Yan, Xingzhuo and Fu, Minghan}, title = {NTIRE 2024 Image Shadow Removal Challenge Report}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {6547-6570} }
NTIRE 2024 Image Shadow Removal Challenge Report
Abstract
This work reviews the results of the NTIRE 2024 Challenge on Shadow Removal. Building on the last year edition the current challenge was organized in two tracks with a track focused on increased fidelity reconstruction and a separate ranking for high performing perceptual quality solutions. Track 1 (fidelity) had 214 registered participants with 17 teams submitting in the final phase while Track 2 (perceptual) registered 185 participants resulting in 18 final phase submissions. Both tracks were based on data from the WSRD dataset simulating interactions between self-shadows and cast shadows with a large variety of represented objects textures and materials. Improved image alignment enabled increased fidelity reconstruction with restored frames mostly indistinguishable from the references images for top performing solutions.
Related Material