18 citations · 35 across the 6 of their papers we have counts for
6 papers
FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features
Yufeng Yin, Di Chang, Guoxian Song +5
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, p…
ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
Jiteng Mu, Shen Sang, Nuno Vasconcelos +1
While NeRF-based human representations have shown impressive novel view synthesis results, most methods still rely on a large number of images / views for training. In this work, w…
AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning
Guoxian Song, Hongyi Xu, Jing Liu +7
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.…
Tag-based annotation creates better avatars
Minghao Liu, Zeyu Cheng, Shen Sang +2
Avatar creation from human images allows users to customize their digital figures in different styles. Existing rendering systems like Bitmoji, MetaHuman, and Google Cartoonset pro…
AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging
Shen Sang, Tiancheng Zhi, Guoxian Song +6
Stylized 3D avatars have become increasingly prominent in our modern life. Creating these avatars manually usually involves laborious selection and adjustment of continuous and dis…
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
Zhengqin Li, Ting-Wei Yu, Shen Sang +14
We propose a novel framework for creating large-scale photorealistic datasets of indoor scenes, with ground truth geometry, material, lighting and semantics. Our goal is to make th…