Bio

I'm Chen Hou, and I've recently received my master's degree at University of Science and Technology of China under the supervision of Prof. Zhibo Chen . My research interests emcompass multiple fields including:

Controllable Visual Generation
Efficient image/video/3D manipulation, prior knowledge of generative models, interaction with other modalities

Extended Reality
I'm extremely interested in XR, I teach myself about them. Check my XR Gallery.

Besides those, I've also studied Reinforcement Learning and its applications in solving sequential decision-making tasks, as well as AI4Science where we modeled a scientific problem in the form of NLP (check this). I'm also interested in 3D relevant topics.


Publication

Training-free Camera Control for Video Generation
Chen Hou, Guoqiang Wei, Yan Zeng, Zhibo Chen
Preprint
Project Page | Paper | Demo

High-Fidelity Diffusion-Based Image Editing
Chen Hou, Guoqiang Wei, Zhibo Chen
AAAI 2024
Paper

Adaptive Hypergraph Convolutional Network for No-Reference 360-degree Image Quality
Jun Fu, Chen Hou, Wei Zhou, Jiahua Xu, and Zhibo Chen
ACM MM 2022
Paper

TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation
Xingrui Wang, Xin Li, Yaosi Hu, Hanxin Zhu, Chen Hou, Cuiling Lan, Zhibo Chen
Preprint


Project

AI4Science: Protein Sequence Generation (Ongoing)
How proteins connect to each other is unknown. But if we find out the law inside it, we can combine untried protein pairs and create new proteins that have never been seen in natural world. This is exciting. We proposed an innovative pipeline to learn how these connections are formed between proteins, and successfully generate comobinations which are nonexistent naturally, but exhibit enhanced functionality.


XR Gallery

Complete gallery is exhibited here. You can also click the selected demos below to see their details.


Experience

AI Lab, ByteDance
Research Intern, Jan. 2024 ~ Jun. 2024


Contact

houchen@mail.ustc.edu.cn