Zobrazeno 1 - 10
of 118
pro vyhledávání: '"Cheng, Yuhao"'
Autor:
Zhang, Shiyue, Chong, Zheng, Zhang, Xujie, Li, Hanhui, Cheng, Yuhao, Yan, Yiqiang, Liang, Xiaodan
General text-to-image models bring revolutionary innovation to the fields of arts, design, and media. However, when applied to garment generation, even the state-of-the-art text-to-image models suffer from fine-grained semantic misalignment, particul
Externí odkaz:
http://arxiv.org/abs/2408.12352
Autor:
Cheng, Junhao, Lu, Xi, Li, Hanhui, Zai, Khun Loun, Yin, Baiqiao, Cheng, Yuhao, Yan, Yiqiang, Liang, Xiaodan
As cutting-edge Text-to-Image (T2I) generation models already excel at producing remarkable single images, an even more challenging task, i.e., multi-turn interactive image generation begins to attract the attention of related research communities. T
Externí odkaz:
http://arxiv.org/abs/2406.01388
4D head capture aims to generate dynamic topological meshes and corresponding texture maps from videos, which is widely utilized in movies and games for its ability to simulate facial muscle movements and recover dynamic textures in pore-squeezing. T
Externí odkaz:
http://arxiv.org/abs/2406.00440
Optical flow estimation is one of the fundamental tasks in low-level computer vision, which describes the pixel-wise displacement and can be used in many other tasks. From the apparent aspect, the optical flow can be viewed as the correlation between
Externí odkaz:
http://arxiv.org/abs/2405.12512
Autor:
Cheng, Junhao, Yin, Baiqiao, Cai, Kaixin, Huang, Minbin, Li, Hanhui, He, Yuxin, Lu, Xi, Li, Yue, Li, Yifei, Cheng, Yuhao, Yan, Yiqiang, Liang, Xiaodan
Recent advances in diffusion models can generate high-quality and stunning images from text. However, multi-turn image generation, which is of high demand in real-world scenarios, still faces challenges in maintaining semantic consistency between ima
Externí odkaz:
http://arxiv.org/abs/2404.18919
Autor:
Huang, Jiehui, Dong, Xiao, Song, Wenhui, Li, Hanhui, Zhou, Jun, Cheng, Yuhao, Liao, Shutao, Chen, Long, Yan, Yiqiang, Liao, Shengcai, Liang, Xiaodan
Diffusion-based technologies have made significant strides, particularly in personalized and customized facialgeneration. However, existing methods face challenges in achieving high-fidelity and detailed identity (ID)consistency, primarily due to ins
Externí odkaz:
http://arxiv.org/abs/2404.16771
Autor:
Ren, Xingyu, Deng, Jiankang, Cheng, Yuhao, Guo, Jia, Ma, Chao, Yan, Yichao, Zhu, Wenhan, Yang, Xiaokang
Recent 3D face reconstruction methods have made remarkable advancements, yet there remain huge challenges in monocular high-quality facial reflectance reconstruction. Existing methods rely on a large amount of light-stage captured data to learn facia
Externí odkaz:
http://arxiv.org/abs/2404.00301
Multimedia compression allows us to watch videos, see pictures and hear sounds within a limited bandwidth, which helps the flourish of the internet. During the past decades, multimedia compression has achieved great success using hand-craft features
Externí odkaz:
http://arxiv.org/abs/2308.09332
Autor:
Wu, Sijing, Yan, Yichao, Li, Yunhao, Cheng, Yuhao, Zhu, Wenhan, Gao, Ke, Li, Xiaobo, Zhai, Guangtao
To bring digital avatars into people's lives, it is highly demanded to efficiently generate complete, realistic, and animatable head avatars. This task is challenging, and it is difficult for existing methods to satisfy all the requirements at once.
Externí odkaz:
http://arxiv.org/abs/2304.03950
Head generation with diverse identities is an important task in computer vision and computer graphics, widely used in multimedia applications. However, current full head generation methods require a large number of 3D scans or multi-view images to tr
Externí odkaz:
http://arxiv.org/abs/2303.15892