SoccerNet 2025 Challenges Results
Abstract
The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understanding. This year's challenges span four vision-based tasks: (1) Team Ball Action Spotting, focused on detecting ball-related actions in football broadcasts and assigning actions to teams; (2) Monocular Depth Estimation, targeting the recovery of scene geometry from single-camera broadcast clips through relative depth estimation for each pixel; (3) Multi-View Foul Recognition, requiring the analysis of multiple synchronized camera views to classify fouls and their severity; and (4) Game State Reconstruction, aimed at localizing and identifying all players from a broadcast video to reconstruct the game state on a 2D top-view of the field. Across all tasks, participants were provided with large-scale annotated datasets, unified evaluation protocols, and strong baselines as starting points. This report presents the results of each challenge, highlights the top-performing solutions, and provides insights into the progress made by the community. The SoccerNet Challenges continue to serve as a driving force for reproducible, open research at the intersection of computer vision, artificial intelligence, and sports. Detailed information about the tasks, challenges, and leaderboards can be found at https://www.soccer-net.org, with baselines and development kits available at https://github.com/SoccerNet.
Cite
@article{arxiv.2508.19182,
title = {SoccerNet 2025 Challenges Results},
author = {Silvio Giancola and Anthony Cioppa and Marc Gutiérrez-Pérez and Jan Held and Carlos Hinojosa and Victor Joos and Arnaud Leduc and Floriane Magera and Karen Sanchez and Vladimir Somers and Artur Xarles and Antonio Agudo and Alexandre Alahi and Olivier Barnich and Albert Clapés and Christophe De Vleeschouwer and Sergio Escalera and Bernard Ghanem and Thomas B. Moeslund and Marc Van Droogenbroeck and Tomoki Abe and Saad Alotaibi and Faisal Altawijri and Steven Araujo and Xiang Bai and Xiaoyang Bi and Jiawang Cao and Vanyi Chao and Kamil Czarnogórski and Fabian Deuser and Mingyang Du and Tianrui Feng and Patrick Frenzel and Mirco Fuchs and Jorge García and Konrad Habel and Takaya Hashiguchi and Sadao Hirose and Xinting Hu and Yewon Hwang and Ririko Inoue and Riku Itsuji and Kazuto Iwai and Hongwei Ji and Yangguang Ji and Licheng Jiao and Yuto Kageyama and Yuta Kamikawa and Yuuki Kanasugi and Hyungjung Kim and Jinwook Kim and Takuya Kurihara and Bozheng Li and Lingling Li and Xian Li and Youxing Lian and Dingkang Liang and Hongkai Lin and Jiadong Lin and Jian Liu and Liang Liu and Shuaikun Liu and Zhaohong Liu and Yi Lu and Federico Méndez and Huadong Ma and Wenping Ma and Jacek Maksymiuk and Henry Mantilla and Ismail Mathkour and Daniel Matthes and Ayaha Motomochi and Amrulloh Robbani Muhammad and Haruto Nakayama and Joohyung Oh and Yin May Oo and Marcelo Ortega and Norbert Oswald and Rintaro Otsubo and Fabian Perez and Mengshi Qi and Cristian Rey and Abel Reyes-Angulo and Oliver Rose and Hoover Rueda-Chacón and Hideo Saito and Jose Sarmiento and Kanta Sawafuji and Atom Scott and Xi Shen and Pragyan Shrestha and Jae-Young Sim and Long Sun and Yuyang Sun and Tomohiro Suzuki and Licheng Tang and Masato Tonouchi and Ikuma Uchida and Henry O. Velesaca and Tiancheng Wang and Rio Watanabe and Jay Wu and Yongliang Wu and Shunzo Yamagishi and Di Yang and Xu Yang and Yuxin Yang and Hao Ye and Xinyu Ye and Calvin Yeung and Xuanlong Yu and Chao Zhang and Dingyuan Zhang and Kexing Zhang and Zhe Zhao and Xin Zhou and Wenbo Zhu and Julian Ziegler},
journal= {arXiv preprint arXiv:2508.19182},
year = {2025}
}