Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Chu, Wenqing"'
While considerable progress has been made in achieving accurate lip synchronization for 3D speech-driven talking face generation, the task of incorporating expressive facial detail synthesis aligned with the speaker's speaking status remains challeng
Externí odkaz:
http://arxiv.org/abs/2402.16124
Autor:
Kong, Lingtong, Jiang, Boyuan, Luo, Donghao, Chu, Wenqing, Tai, Ying, Wang, Chengjie, Yang, Jie
Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience. Existing methods have achieved great success by employing advanced motion models and synthesis networks. However, the sp
Externí odkaz:
http://arxiv.org/abs/2309.03508
Autor:
Li, Xin, Chu, Wenqing, Wu, Ye, Yuan, Weihang, Liu, Fanglong, Zhang, Qi, Li, Fu, Feng, Haocheng, Ding, Errui, Wang, Jingdong
In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an off-the-shelf text-to
Externí odkaz:
http://arxiv.org/abs/2309.00398
Autor:
Xu, Chao, Zhu, Junwei, Zhang, Jiangning, Han, Yue, Chu, Wenqing, Tai, Ying, Wang, Chengjie, Xie, Zhifeng, Liu, Yong
Recently, emotional talking face generation has received considerable attention. However, existing methods only adopt one-hot coding, image, or audio as emotion conditions, thus lacking flexible control in practical applications and failing to handle
Externí odkaz:
http://arxiv.org/abs/2305.02572
Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a
Externí odkaz:
http://arxiv.org/abs/2207.10315
Autor:
Kong, Lingtong, Jiang, Boyuan, Luo, Donghao, Chu, Wenqing, Huang, Xiaoming, Tai, Ying, Wang, Chengjie, Yang, Jie
Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications. In
Externí odkaz:
http://arxiv.org/abs/2205.14620
Autor:
Chen, Yifeng, Chu, Wenqing, Wang, Fangfang, Tai, Ying, Yi, Ran, Gan, Zhenye, Yao, Liang, Wang, Chengjie, Li, Xi
Recently, there is growing attention on one-stage panoptic segmentation methods which aim to segment instances and stuff jointly within a fully convolutional pipeline efficiently. However, most of the existing works directly feed the backbone feature
Externí odkaz:
http://arxiv.org/abs/2201.04796
Autor:
Wang, Yuhan, Chen, Xu, Zhu, Junwei, Chu, Wenqing, Tai, Ying, Wang, Chengjie, Li, Jilin, Wu, Yongjian, Huang, Feiyue, Ji, Rongrong
In this work, we propose a high fidelity face swapping method, called HifiFace, which can well preserve the face shape of the source face and generate photo-realistic results. Unlike other existing face swapping works that only use face recognition m
Externí odkaz:
http://arxiv.org/abs/2106.09965
Autor:
Zhang, Wendong, Zhu, Junwei, Tai, Ying, Wang, Yunbo, Chu, Wenqing, Ni, Bingbing, Wang, Chengjie, Yang, Xiaokang
Recent advances in image inpainting have shown impressive results for generating plausible visual details on rather simple backgrounds. However, for complex scenes, it is still challenging to restore reasonable contents as the contextual information
Externí odkaz:
http://arxiv.org/abs/2106.07220
Autor:
Chao, Xianjin, Bin, Yanrui, Chu, Wenqing, Cao, Xuan, Ge, Yanhao, Wang, Chengjie, Li, Jilin, Huang, Feiyue, Leung, Howard
Human motion prediction aims to predict future 3D skeletal sequences by giving a limited human motion as inputs. Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend, but motion details
Externí odkaz:
http://arxiv.org/abs/2011.11221