Zobrazeno 1 - 10
of 3 098
pro vyhledávání: '"Tao, Xin"'
Autor:
Tian, Ye, Yang, Ling, Yang, Haotian, Gao, Yuan, Deng, Yufan, Chen, Jingmin, Wang, Xintao, Yu, Zhaochen, Tao, Xin, Wan, Pengfei, Zhang, Di, Cui, Bin
Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in object numbe
Externí odkaz:
http://arxiv.org/abs/2406.04277
Autor:
Shen, Guibao, Wang, Luozhou, Lin, Jiantao, Ge, Wenhang, Zhang, Chaozhe, Tao, Xin, Zhang, Yuan, Wan, Pengfei, Wang, Zhongyuan, Chen, Guangyong, Li, Yijun, Chen, Ying-Cong
Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accur
Externí odkaz:
http://arxiv.org/abs/2405.15321
Autor:
Liu, Xiaohong, Min, Xiongkuo, Zhai, Guangtao, Li, Chunyi, Kou, Tengchuan, Sun, Wei, Wu, Haoning, Gao, Yixuan, Cao, Yuqin, Zhang, Zicheng, Wu, Xiele, Timofte, Radu, Peng, Fei, Fu, Huiyuan, Ming, Anlong, Wang, Chuanming, Ma, Huadong, He, Shuai, Dou, Zifei, Chen, Shu, Zhang, Huacong, Xie, Haiyi, Wang, Chengwei, Chen, Baoying, Zeng, Jishen, Yang, Jianquan, Wang, Weigang, Fang, Xi, Lv, Xiaoxin, Yan, Jun, Zhi, Tianwu, Zhang, Yabin, Li, Yaohui, Li, Yang, Xu, Jingwen, Liu, Jianzhao, Liao, Yiting, Li, Junlin, Yu, Zihao, Lu, Yiting, Li, Xin, Motamednia, Hossein, Hosseini-Benvidi, S. Farhad, Guan, Fengbin, Mahmoudi-Aznaveh, Ahmad, Mansouri, Azadeh, Gankhuyag, Ganzorig, Yoon, Kihwan, Xu, Yifang, Fan, Haotian, Kong, Fangyuan, Zhao, Shiling, Dong, Weifeng, Yin, Haibing, Zhu, Li, Wang, Zhiling, Huang, Bingchen, Saha, Avinab, Mishra, Sandeep, Gupta, Shashank, Sureddi, Rajesh, Saha, Oindrila, Celona, Luigi, Bianco, Simone, Napoletano, Paolo, Schettini, Raimondo, Yang, Junfeng, Fu, Jing, Zhang, Wei, Cao, Wenzhi, Liu, Limei, Peng, Han, Yuan, Weijun, Li, Zhan, Cheng, Yihang, Deng, Yifan, Li, Haohui, Qu, Bowen, Li, Yao, Luo, Shuqing, Wang, Shunzhou, Gao, Wei, Lu, Zihao, Conde, Marcos V., Wang, Xinrui, Chen, Zhibo, Liao, Ruling, Ye, Yan, Wang, Qiulin, Li, Bing, Zhou, Zhaokun, Geng, Miao, Chen, Rui, Tao, Xin, Liang, Xiaoyu, Sun, Shangkun, Ma, Xingyuan, Li, Jiaze, Yang, Mengduo, Xu, Haoran, Zhou, Jie, Zhu, Shiding, Yu, Bohan, Chen, Pengfei, Xu, Xinrui, Shen, Jiabin, Duan, Zhichao, Asadi, Erfan, Liu, Jiahe, Yan, Qi, Qu, Youran, Zeng, Xiaohui, Wang, Lele, Liao, Renjie
This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major
Externí odkaz:
http://arxiv.org/abs/2404.16687
Autor:
Zhou, Zhaokun, Wang, Qiulin, Lin, Bin, Su, Yiwei, Chen, Rui, Tao, Xin, Zheng, Amin, Yuan, Li, Wan, Pengfei, Zhang, Di
As an alternative to expensive expert evaluation, Image Aesthetic Assessment (IAA) stands out as a crucial task in computer vision. However, traditional IAA methods are typically constrained to a single data source or task, restricting the universali
Externí odkaz:
http://arxiv.org/abs/2404.09619
Previous methods for Video Frame Interpolation (VFI) have encountered challenges, notably the manifestation of blur and ghosting effects. These issues can be traced back to two pivotal factors: unavoidable motion errors and misalignment in supervisio
Externí odkaz:
http://arxiv.org/abs/2404.06692
Autor:
Wang, Luozhou, Shen, Guibao, Liang, Yixun, Tao, Xin, Wan, Pengfei, Zhang, Di, Li, Yijun, Chen, Yingcong
In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models. Recognizing the unique challenges posed by v
Externí odkaz:
http://arxiv.org/abs/2403.20193
Autor:
Zhang, Tao, Tian, Xingye, Zhou, Yikang, Ji, Shunping, Wang, Xuebo, Tao, Xin, Zhang, Yuan, Wan, Pengfei, Wang, Zhongyuan, Wu, Yu
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and vi
Externí odkaz:
http://arxiv.org/abs/2312.13305
Autor:
Fan, Qi, Tao, Xin, Ke, Lei, Ye, Mingqiao, Zhang, Yuan, Wan, Pengfei, Wang, Zhongyuan, Tai, Yu-Wing, Tang, Chi-Keung
The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive analysis o
Externí odkaz:
http://arxiv.org/abs/2311.15776
Autor:
Zhang, Tao, Tian, Xingye, Zhou, Yikang, Wu, Yu, Ji, Shunping, Yan, Cilin, Wang, Xuebo, Tao, Xin, Zhang, Yuan, Wan, Pengfei
Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report, we present further improvements to the SOTA VIS method, DVIS. First,
Externí odkaz:
http://arxiv.org/abs/2308.14392
Existing methods for interactive segmentation in radiance fields entail scene-specific optimization and thus cannot generalize across different scenes, which greatly limits their applicability. In this work we make the first attempt at Scene-Generali
Externí odkaz:
http://arxiv.org/abs/2308.05104