|
Hao-Yu (Max) Hsu I am a 2nd year M.S. (thesis) student in Computer Science at University of Illinois Urbana-Champaign, advised by Prof. Shenlong Wang. I am honored to receive Siebel Scholars Award, Class of 2025. My research interests lie in 3D vision, neural rendering, and multimodal learning. My long-term goal is to develop AR/VR tools that model and reconsturct our physical world, and make realistic simulations accessible to everyone. Previously, I was fortunate to have been advised by Prof. Yu-Chiang Frank Wang and Prof. Shao-Hua Sun at National Taiwan University. I received my Bachelor's degree in Electrical Engineering from National Tsing Hua University in 2021 the highest distinction (summa cum laude). I am applying for 2025 Fall Ph.D. positions and actively seeking for research-oriented internships for 2025 Summer. Please feel free to reach out if you believe I am a good candidate. |
|
Selected Publications(* denotes equal contribution) |
 
|
AutoVFX: Physically Realistic Video Editing from Natural Language Instructions
Hao-Yu Hsu, Zhi-Hao Lin, Albert J. Zhai, Hongchi Xia, Shenlong Wang 3DV, 2025 paper / project page / code A system that generates dynamic, physically realistic visual effects (VFX) on a single video solely from text-based editing instructions. |
 
|
SPoVT: Semantic Prototype Variational Transformer for Dense Point Cloud Semantic Completion
Hao-Yu Hsu*, Sheng-Yu Huang*, Yu-Chiang Frank Wang NeurIPS, 2022 paper / project page / code / video A point cloud semantic completion framework to complete partial point clouds of 3D objects with variational Transformer. |
 
|
NeurMiPs: Neural Mixture of Planar Experts for View Synthesis
Zhi-Hao Lin, Wei-Chiu Ma*, Hao-Yu Hsu*, Yu-Chiang Frank Wang, Shenlong Wang CVPR, 2022 paper / project page / code / video Use a novel 3D planar representation to model the geometry and appearance of a scene for view synthesis. |
Other Publications |
 
|
Interpreting Latent Representation In Neural Radiance Fields for Manipulating Object Semantics
Yu-Shan Huang, Sheng-Yu Huang, Hao-Yu Hsu, Yu-Chiang Frank Wang ICIP, 2023 paper A method for semantic-aware manipulation on generative NeRF by controlling latent representation. |
Education |
|
|
University of Illinois at Urbana-Champaign
|  |
|
National Tsing Hua University
|  |
Experience |
|
|
Shenlong's Lab, UIUC CS
| |
|
Robot Learning Lab, National Taiwan University
|  |
|
Vision & Learning Lab, National Taiwan University
| |
Teaching Experience |
|
UIUC CS (CS 233: Computer Architecture, Spring 2024 | CS543: Computer Vision, Fall 2024) NTHU EE (EE 2405: Embedded System Laboratory, Spring 2019) |
Awards & Professional Activity |
|
|
Credits to Jon Barron for this awesome website template. |