Guoxian Song

Guoxian Song

Auto-generated profile, based on publicly available information

Guoxian Song

Nanyang Technological University Singapore

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2024
Verified
Conference Paper
Open access
YXYou Xie
You Xie
HXHongyi Xu
Hongyi Xu
GSGuoxian Song
Guoxian Song
CWChao Wang
Chao Wang
YSYichun Shi
Yichun Shi
LLLinjie Luo
Linjie Luo
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 from a driving video, capturing both highly dynamic and subtle facial expressions along with wide-range head movements. As its core, we leverage the generative prior of a pre-trained diffusion model as the rendering backbone, while achieve fine-grained head pose and expression control with novel controlling signals within the framework of ControlNet. In contrast to conventional coarse explicit controls such as facial landmarks, our motion control module is learned to interpret the dynamics directly from the original driving RGB inputs. The motion accuracy is further enhanced with a patch-based local control module that effectively enhance the motion attention to small-scale nuances like eyeball positions. Notably, to mitigate the identity leakage from the driving signals, we train our motion control modules with scaling-augmented cross-identity images, ensuring maximized disentanglement from the appearance reference modules. Experimental results demonstrate the universal effectiveness of X-Portrait across a diverse range of facial portraits and expressive driving sequences, and showcase its proficiency in generating captivating portrait animations with consistently maintained identity characteristics.

28 September 2021 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
CZChuanxia Zheng
Chuanxia Zheng
DDDuy-Son Dao
Duy-Son Dao
GSGuoxian Song
Guoxian Song
TCTat-Jen Cham
Tat-Jen Cham
JCJianfei Cai
Jianfei Cai

21 May 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CZChuanxia Zheng
Chuanxia Zheng
GSGuoxian Song
Guoxian Song
TCTat-Jen Cham
Tat-Jen Cham
JCJianfei Cai
Jianfei Cai
LLLinjie Luo
Linjie Luo
DPDinh Phung
Dinh Phung
We introduce PICFormer, a novel framework for P luralistic I mage C ompletion using a trans Former based architecture, that achieves both high quality and diversity at a much faster inference speed. Our key contribution is to introduce a code-shared codebook learning using a restrictive CNN on small and non-overlapping receptive fields (RFs) for the local visible token representation. This results in a compact yet expressive discrete representation, facilitating efficient modeling of global visible context relations by the transformer. Unlike the prevailing autoregressive approaches, we proposed to sample all tokens simultaneously, leading to more than 100× faster inference speed. To enhance appearance consistency between visible and generated regions, we further propose a novel attention-aware layer (AAL), designed to better exploit distantly related high-frequency features. Through extensive experiments, we demonstrate that the PICFormer efficiently learns semantically-rich discrete codes, resulting in significantly improved image quality. Moreover, our diverse image completion framework surpasses State-of-the-Art methods on multiple image completion datasets.

1 July 2021 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
GSGuoxian Song
Guoxian Song
TCTat‐Jen Cham
Tat‐Jen Cham
JCJianfei Cai
Jianfei Cai
JZJianmin Zheng
Jianmin Zheng

14 December 2025
Verified
Conference Paper
Open access
GSGuoxian Song
Guoxian Song
HXHongyi Xu
Hongyi Xu
XZXiaochen Zhao
Xiaochen Zhao
YXYou Xie
You Xie
TGTianpei Gu
Tianpei Gu
LLLinjie Luo
Linjie Luo

14 December 2025
Verified
Conference Paper
Open access
CZChenxu Zhang
Chenxu Zhang
ZLZenan Li
Zenan Li
HXHongyi Xu
Hongyi Xu
YXYou Xie
You Xie
XZXiaochen Zhao
Xiaochen Zhao
LLLinjie Luo
Linjie Luo