Hi there!
Welcome to the website of Hanyang Kong (εζζΈ). π
I am honored to be pursuing my Ph.D. at the Learning and Vision Lab @ NUS, advised by Prof. Xinchao Wang since August 2021. My academic journey in computer science previously led me to Xiβan Jiaotong University, where I completed my masterβs degree under the mentorship of Prof. Qingyu Yang. π
My research is centered on AIGC (Artificial Intelligence-Generated Content) and LLM (Large Language Models), focusing on:
- π 3D Generation and Estimation: Striving to contribute to the evolution of digital modeling.
- π‘ Diffusion Models and LLM Applications: Aiming to bridge advanced AI with real-world applications.
Thank you for your interest. Please feel free to explore the site to learn more about my research and academic endeavors. π
π₯ News
- 2024.07: Β ππ Our paper DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators was accepted by ECCVβ24.
- 2023.12: Β ππ πOur new work, DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators, is released! Check our paper and code! Also, please feel free to try our online huggingface demo!
- 2023.07: Β ππ Our paper Priority-centric human motion generation in discrete latent space was accepted by ICCVβ23.
π Publications
![sym](images/dreamdrone.png)
DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators
Hanyang Kong, Dongze Lian, Michael Bi Mi, Xinchao Wang
Project page, Huggingface demo, Code, Arxiv
- Zero-shot, Training-Free Scene Creation: Generates perceptual scenes directly from text, without specific training for each scene.
- Click-Guided Dreamscapes Navigation: Allows drone flight control through point selection, offering a visually immersive experience.
- Resource-Efficient Scene Generation: Omits the need for a 3D point cloud, enabling faster scene creation with lower computational demand.
![sym](images/t2m.jpg)
Priority-Centric Human Motion Generation in Discrete Latent Space
Hanyang Kong, Kehong Gong, Dongze Lian, Michael Bi Mi, Xinchao Wang
- Text-to-motion generation in descrete latent space.
- Priority-centric diffusion scheme for the discrete diffusion model.
π Educations
- 2021.08 - present: Ph.D. candidate in College of Design and Engineering, National University of Singapore.
- 2017.08 - 2020.06: M.Eng. in Faculty of Electronic and Information Engineering, Xiβan Jiaotong University.
- 2013.08 - 2017.06: B.Eng. in Faculty of Electrical Engineering and Automation, Hefei University of Technology.