Zobrazeno 1 - 10
of 268
pro vyhledávání: '"Han Xintong"'
Current diffusion models for human image animation struggle to ensure identity (ID) consistency. This paper presents StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-
Externí odkaz:
http://arxiv.org/abs/2411.17697
In this paper, we introduce MRStyle, a comprehensive framework that enables color style transfer using multi-modality reference, including image and text. To achieve a unified style feature space for both modalities, we first develop a neural network
Externí odkaz:
http://arxiv.org/abs/2409.05250
Autor:
Tu, Shuyuan, Dai, Qi, Zhang, Zihao, Xie, Sicheng, Cheng, Zhi-Qi, Luo, Chong, Han, Xintong, Wu, Zuxuan, Jiang, Yu-Gang
Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and background. In this
Externí odkaz:
http://arxiv.org/abs/2405.20325
Abstract: Cover song identification (CSI) focuses on finding the same music with different versions in reference anchors given a query track. In this paper, we propose a novel system named CoverHunter that overcomes the shortcomings of existing detec
Externí odkaz:
http://arxiv.org/abs/2306.09025
Autor:
Qian, Lihui, Han, Xintong, Wang, Faqiang, Liu, Hongyu, Dong, Haoye, Li, Zhiwen, Wei, Huawei, Lin, Zhe, Jin, Cheng-Bin
We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that estimates 3D h
Externí odkaz:
http://arxiv.org/abs/2305.11101
Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming tasks. Such a trade-off is referred to as the stability-plasticity dile
Externí odkaz:
http://arxiv.org/abs/2303.07223
Autor:
Liu, Hongyu, Han, Xintong, Jin, Chengbin, Qian, Lihui, Wei, Huawei, Lin, Zhe, Wang, Faqiang, Dong, Haoye, Song, Yibing, Xu, Jia, Chen, Qifeng
Human motion transfer aims to transfer motions from a target dynamic person to a source static one for motion synthesis. An accurate matching between the source person and the target motion in both large and subtle motion changes is vital for improvi
Externí odkaz:
http://arxiv.org/abs/2302.11306
Autor:
Zhu, Yiming, Liu, Hongyu, Song, Yibing, Yuan, ziyang, Han, Xintong, Yuan, Chun, Chen, Qifeng, Wang, Jue
Free-form text prompts allow users to describe their intentions during image manipulation conveniently. Based on the visual latent space of StyleGAN[21] and text embedding space of CLIP[34], studies focus on how to map these two latent spaces for tex
Externí odkaz:
http://arxiv.org/abs/2210.07883
Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the entire netwo
Externí odkaz:
http://arxiv.org/abs/2209.15210
Autor:
Zong, Yunhe 1, Li, Yunlei 1, Sun, Yanyan, Han, Xintong, Yuan, Jingwei, Ma, Lin, Ma, Hui, Chen, Jilan ⁎
Publikováno v:
In Poultry Science February 2025 104(2)
