Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Nie, Xuecheng"'
Autor:
Zhang, Yang, Zhang, Rui, Nie, Xuecheng, Li, Haochen, Chen, Jikun, Hao, Yifan, Zhang, Xin, Liu, Luoqi, Li, Ling
Recent text-to-image models have achieved remarkable success in generating high-quality images. However, when tasked with multi-concept generation which creates images containing multiple characters or objects, existing methods often suffer from attr
Externí odkaz:
http://arxiv.org/abs/2409.01327
Autor:
Zhao, Jian, Jin, Lei, Li, Jianshu, Zhu, Zheng, Teng, Yinglei, Zhao, Jiaojiao, Gulshad, Sadaf, Wang, Zheng, Zhao, Bo, Shu, Xiangbo, Wei, Yunchao, Nie, Xuecheng, Jin, Xiaojie, Liang, Xiaodan, Satoh, Shin'ichi, Guo, Yandong, Lu, Cewu, Xing, Junliang, Shengmei, Jane Shen
The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding. The SkatingVerse dataset used for the SkatingVerse Challenge has been publicly released. There are two subsets i
Externí odkaz:
http://arxiv.org/abs/2405.17188
Autor:
Qiu, Xinmin, Han, Congying, Zhang, Zicheng, Li, Bonan, Guo, Tiande, Wang, Pingyu, Nie, Xuecheng
Developing blind video deflickering (BVD) algorithms to enhance video temporal consistency, is gaining importance amid the flourish of image processing and video generation. However, the intricate nature of video data complicates the training of deep
Externí odkaz:
http://arxiv.org/abs/2403.06243
Autor:
He, Runze, Huang, Shaofei, Nie, Xuecheng, Hui, Tianrui, Liu, Luoqi, Dai, Jiao, Han, Jizhong, Li, Guanbin, Liu, Si
In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt. However, obtaining desired editing results conformed with the editin
Externí odkaz:
http://arxiv.org/abs/2312.01663
Existing works have advanced Text-to-Image (TTI) diffusion models for video editing in a one-shot learning manner. Despite their low requirements of data and computation, these methods might produce results of unsatisfied consistency with text prompt
Externí odkaz:
http://arxiv.org/abs/2305.17431
Blind face restoration (BFR) is important while challenging. Prior works prefer to exploit GAN-based frameworks to tackle this task due to the balance of quality and efficiency. However, these methods suffer from poor stability and adaptability to lo
Externí odkaz:
http://arxiv.org/abs/2305.04517
This paper focuses on face stylization with a single artistic target. Existing works for this task often fail to retain the source content while achieving geometry variation. Here, we present a novel StyO model, ie. Stylize the face in only One-shot,
Externí odkaz:
http://arxiv.org/abs/2303.03231
Contrastive learning (CL) has shown great power in self-supervised learning due to its ability to capture insight correlations among large-scale data. Current CL models are biased to learn only the ability to discriminate positive and negative pairs
Externí odkaz:
http://arxiv.org/abs/2211.09013
Existing methods for human mesh recovery mainly focus on single-view frameworks, but they often fail to produce accurate results due to the ill-posed setup. Considering the maturity of the multi-view motion capture system, in this paper, we propose t
Externí odkaz:
http://arxiv.org/abs/2210.01886
Autor:
Li, Bonan, Hu, Yinhan, Nie, Xuecheng, Han, Congying, Jiang, Xiangjian, Guo, Tiande, Liu, Luoqi
In this paper, we focus on analyzing and improving the dropout technique for self-attention layers of Vision Transformer, which is important while surprisingly ignored by prior works. In particular, we conduct researches on three core questions: Firs
Externí odkaz:
http://arxiv.org/abs/2208.02646