SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop
Hamann, Friedhelm, Mededovic, Emil, Gülhan, Fabian, Wu, Yuli, Stegmaier, Johannes, He, Jing, Wang, Yiqing, Zhang, Kexin, Li, Lingling, Jiao, Licheng, Ma, Mengru, Huang, Hongxiang, Yan, Yuhao, Ren, Hongwei, Lin, Xiaopeng, Huang, Yulong, Cheng, Bojun, Lee, Se Hyun, Ham, Gyu Sung, Oh, Kanghan, Lim, Gi Hyun, Yang, Boxuan, Du, Bowen, Gallego, Guillermo
–arXiv.org Artificial Intelligence
W e present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision W orkshop. The task is to predict accurate pixel-level segmentation masks of defined object classes from spatio-temporally aligned event camera and grayscale camera data. W e provide an overview of the task, dataset, challenge details and results. Furthermore, we describe the methods used by the top-5 ranking teams in the challenge. More resources and code of the participants' methods are available here: https:// github.com/
arXiv.org Artificial Intelligence
Aug-19-2025