Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Song, Guoxian"'
Autor:
Xu, Zhongcong, Song, Chaoyue, Song, Guoxian, Zhang, Jianfeng, Liew, Jun Hao, Xu, Hongyi, Xie, You, Luo, Linjie, Lin, Guosheng, Feng, Jiashi, Shou, Mike Zheng
Recent advances in video diffusion models have enabled realistic and controllable human image animation with temporal coherence. Although generating reasonable results, existing methods often overlook the need for regional supervision in crucial area
Externí odkaz:
http://arxiv.org/abs/2409.19580
We propose X-Portrait, an innovative conditional diffusion model tailored for generating expressive and temporally coherent portrait animation. Specifically, given a single portrait as appearance reference, we aim to animate it with motion derived fr
Externí odkaz:
http://arxiv.org/abs/2403.15931
Autor:
Zhang, Chenxu, Wang, Chao, Zhang, Jianfeng, Xu, Hongyi, Song, Guoxian, Xie, You, Luo, Linjie, Tian, Yapeng, Guo, Xiaohu, Feng, Jiashi
The generation of emotional talking faces from a single portrait image remains a significant challenge. The simultaneous achievement of expressive emotional talking and accurate lip-sync is particularly difficult, as expressiveness is often compromis
Externí odkaz:
http://arxiv.org/abs/2312.13578
Autor:
Gu, Yuming, Xie, You, Xu, Hongyi, Song, Guoxian, Shi, Yichun, Chang, Di, Yang, Jing, Luo, Linjie
We present DiffPortrait3D, a conditional diffusion model that is capable of synthesizing 3D-consistent photo-realistic novel views from as few as a single in-the-wild portrait. Specifically, given a single RGB input, we aim to synthesize plausible bu
Externí odkaz:
http://arxiv.org/abs/2312.13016
Autor:
Chang, Di, Shi, Yichun, Gao, Quankai, Fu, Jessica, Xu, Hongyi, Song, Guoxian, Yan, Qing, Zhu, Yizhe, Yang, Xiao, Soleymani, Mohammad
In this work, we propose MagicPose, a diffusion-based model for 2D human pose and facial expression retargeting. Specifically, given a reference image, we aim to generate a person's new images by controlling the poses and facial expressions while kee
Externí odkaz:
http://arxiv.org/abs/2311.12052
Autor:
Zhang, Xuanmeng, Zhang, Jianfeng, Chacko, Rohan, Xu, Hongyi, Song, Guoxian, Yang, Yi, Feng, Jiashi
We study the problem of 3D-aware full-body human generation, aiming at creating animatable human avatars with high-quality textures and geometries. Generally, two challenges remain in this field: i) existing methods struggle to generate geometries wi
Externí odkaz:
http://arxiv.org/abs/2310.02714
Autor:
Yin, Yufeng, Chang, Di, Song, Guoxian, Sang, Shen, Zhi, Tiancheng, Liu, Jing, Luo, Linjie, Soleymani, Mohammad
Automatic detection of facial Action Units (AUs) allows for objective facial expression analysis. Due to the high cost of AU labeling and the limited size of existing benchmarks, previous AU detection methods tend to overfit the dataset, resulting in
Externí odkaz:
http://arxiv.org/abs/2308.12380
Autor:
Xu, Hongyi, Song, Guoxian, Jiang, Zihang, Zhang, Jianfeng, Shi, Yichun, Liu, Jing, Ma, Wanchun, Feng, Jiashi, Luo, Linjie
We present OmniAvatar, a novel geometry-guided 3D head synthesis model trained from in-the-wild unstructured images that is capable of synthesizing diverse identity-preserved 3D heads with compelling dynamic details under full disentangled control ov
Externí odkaz:
http://arxiv.org/abs/2303.15539
Autor:
Chen, Shuhong, Zhang, Kevin, Shi, Yichun, Wang, Heng, Zhu, Yiheng, Song, Guoxian, An, Sizhe, Kristjansson, Janus, Yang, Xiao, Zwicker, Matthias
We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters. Our anime-style domain poses unique challenges to single-view reconstruction; compared to natural images of human
Externí odkaz:
http://arxiv.org/abs/2303.14587
Autor:
Song, Guoxian, Xu, Hongyi, Liu, Jing, Zhi, Tiancheng, Shi, Yichun, Zhang, Jianfeng, Jiang, Zihang, Feng, Jiashi, Sang, Shen, Luo, Linjie
While substantial progresses have been made in automated 2D portrait stylization, admirable 3D portrait stylization from a single user photo remains to be an unresolved challenge. One primary obstacle here is the lack of high quality stylized 3D trai
Externí odkaz:
http://arxiv.org/abs/2303.14297