Guanwen Feng

I am a third-year PhD candidate at Xidian University of China, supervised by Prof. Qiguang Miao from Xidian University of China.

Welcome to exchange academic and life with me.

My areas of focus include 2D/3D Talking Head Generation, Sign Language Generation and Other AIGC Applications.

Email  /  Github

profile photo
Research
gaussianface [ICASSP 2025] Gaussian-Face: Talking Head Generation with Hybrid Density via 3D Gaussian Splatting
Guanwen Feng, YiLin Zhang, Yunan Li, Siyu Jin, Qiguang Miao
Project /

We propose a novel 3D Gaussian-based talking head generation method.

kanface [ICASSP 2025] KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation
Guanwen Feng, Siyu Jin, Zhihao Qian, Yunan Li, Qiguang Miao
Project /

We propose a novel 3D Gaussian-based talking head generation method.

signmamba [ICASSP 2025] Sign-Mamba: Advanced Mamba-Based Sign Language Generation
Guanwen Feng, YiLin Zhang, Yunan Li, An Liu, Qiguang Miao
Project /

We propose a two-stage generative framework for sign language generation, called Sign-Mamba, based on the state selection mechanism of SSM.

lestalker
[Arxiv 2024] LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space
Guanwen Feng, Zhihao Qian, Yunan Li, Siyu Jin, Qiguang Miao, Chi-Man Pun
Project / Arxiv

We propose a novel one-shot talking head generation model with high interpretability, designed to achieve fine-grained emotion editing across emotion types, levels, and facial units.

emospeaker [Arxiv 2024] EmoSpeaker: One-shot Fine-grained Emotion-Controlled Talking Face Generation
Guanwen Feng, Haoran Cheng, Yunan Li, Zhiyuan Ma, Chaoneng Li, Zhihao Qian, Qiguang Miao, Chi-Man Pun
Project / Arxiv

We propose a novel one-shot fine-grained emotion-controlled talking head generation model.

difftad
[KBS 2024] DiffTAD: Denoising diffusion probabilistic models for vehicle trajectory anomaly detection
Chaoneng Li, Guanwen Feng, Yunan Li, Ruyi Liu, Qiguang Miao, Liang Chang
KBS Code

We propose a denoising-diffusion-based vehicle trajectory anomaly detection pipeline, called DiffTAD.

meacp
[Computers in Biology and Medicine 2022]ME-ACP: Multi-view Neural Networks with Ensemble Model for identification of Anticancer Peptides
Guanwen Feng, Hang Yao, Chaoneng Li, Ruyi Liu, Rungeng Huang, Xiaopeng Fan, Ruiquan Ge, Qiguang Miao,
Project / arXiv / Code

We propose An Ensemble Model for Identification of Anticancer Peptides.


Last updated: Sep. 2024
Web page design credit to Jon Barron