Ding-Jiun Huang

I am a first-year PhD student at the University of Toronto, advised by Prof. David Lindell. Previously, I was a master student at Carnegie Mellon University, advised by Prof. Fernando de la Torre and Prof. Cheng Zhang. My researches focus on digital human reconstruction, including 3D head avatar and simulation-ready 3D garment reconstruction. Prior to this, I had the previlege to be advised by Prof. Yu-Chiang Frank Wang and Dr. Cheng Sun from NVIDIA Research.

I completed my undergraduate studies at National Taiwan University, and had the pleasure to work with Prof. Chung-Wei Lin in my undergraduate research for autonomous vehicles motion planning.

Email  /  CV  /  Scholar  

Given a single in-the-wild image of a human garment, OmniFabric synthesizes the simulation-ready 3D garment through generating textured sewing patterns.

Given a low-resolution 3D head avatar reconstructed from low-quality captures, SuperHead super-resolves high-fidelity geometry and detailed textures while ensuring multiview and temporal consistency under diverse facial expressions.

Given a neural radiance field optimized from low-quality capturings, our generalizable approach directly enhances the 3D representation, leading to high-quality renderings.

Proposing a stack-based framework for video quality assessment (VQA) of videos enhanced by deep-learning-based methods.

Developing a motion planning algorithm for autonomous vehicles to handle malicious attack and communication faults in a platooning system.

This personal page template was borrowed from source code.