Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Zhan, Zitong"'
Autor:
Wang, Chen, Ji, Kaiyi, Geng, Junyi, Ren, Zhongqiang, Fu, Taimeng, Yang, Fan, Guo, Yifan, He, Haonan, Chen, Xiangyu, Zhan, Zitong, Du, Qiwei, Su, Shaoshu, Li, Bowen, Qiu, Yuheng, Du, Yi, Li, Qihang, Yang, Yifan, Lin, Xiao, Zhao, Zhipeng
Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from generalizing well to ever-changing environments. Moreover, collecting larg
Externí odkaz:
http://arxiv.org/abs/2406.16087
Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature correspondence lea
Externí odkaz:
http://arxiv.org/abs/2312.02141
Autor:
Zhan, Zitong, Li, Xiangfu, Li, Qihang, He, Haonan, Pandey, Abhinav, Xiao, Haitao, Xu, Yangmengfei, Chen, Xiangyu, Xu, Kuan, Cao, Kun, Zhao, Zhipeng, Wang, Zihan, Xu, Huan, Fang, Zihang, Chen, Yutian, Wang, Wentao, Fang, Xu, Du, Yi, Wu, Tianhao, Lin, Xiao, Qiu, Yuheng, Yang, Fan, Shi, Jingnan, Su, Shaoshu, Lu, Yiren, Fu, Taimeng, Dantu, Karthik, Wu, Jiajun, Xie, Lihua, Hutter, Marco, Carlone, Luca, Scherer, Sebastian, Huang, Daning, Hu, Yaoyu, Geng, Junyi, Wang, Chen
PyPose is an open-source library for robot learning. It combines a learning-based approach with physics-based optimization, which enables seamless end-to-end robot learning. It has been used in many tasks due to its meticulously designed application
Externí odkaz:
http://arxiv.org/abs/2309.13035
Recently, transformer-based methods have achieved impressive results on Video Instance Segmentation (VIS). However, most of these top-performing methods run in an offline manner by processing the entire video clip at once to predict instance mask vol
Externí odkaz:
http://arxiv.org/abs/2211.09108
This work studies feature representations for dense label propagation in video, with a focus on recently proposed methods that learn video correspondence using self-supervised signals such as colorization or temporal cycle consistency. In the literat
Externí odkaz:
http://arxiv.org/abs/2203.05553