Chung-Ho (Kenneth) Wu, 吳中赫

I am currently pursuing my Master's degree at National Yang Ming Chiao Tung University (It was called National Chiao Tung University before), majoring Multimedia Engineering in College of Computer Science, and advised by Prof. Yu-Lun, Liu at CompPhoto Lab, specializing in 3D computer vision. I earned my bachelor's degree in Computer Science in National Yang Ming Chiao Tung University in 2023.

In addition, I previously worked at ITRI as a 3D Modeling Intern, focusing on the research of 3D reconstruction. I also worked at Qualcomm as an AISW intern, focusing on projects related to LLM and model converters. Currently, I am working at ColegaAI as an AI and Computer Vision Intern.

Email  /  CV  /  GitHub  /  Linkedin

latest update: 2025-02-10

profile gif
profile photo

Try hovering on the profile photo!
(generated by link)

News ! ! !

[2025/02/10] Release AuraFusion360 project page and arXiv paper.

[2024/10/21] Release FrugalNeRF project page and arXiv paper.

Experiences

ColegaAI icon AI and Computer Vision Intern @ ColegaAI : 2025-01 - present

ColegaAI icon AISW Intern @ Qualcomm : 2024-04 - 2024-10

ITRI icon 3D Modeling Intern @ ITRI : 2023-04 - 2023-08

Publications

I'm interested in computer vision, machine learning, image processing, XR, robotics topics. Currently, Most of my research is about novel view synthesis and generative ai.

AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360° Unbounded Scene Inpainting
Chung-Ho Wu*, Yang-Jung Chen*, Ying-Haun Chen, Jie-Ying Lee, Bo-Hsu Ke, Chun-Wei Tuan Mu Yi-Chuan Huang Ching-Yang Lin, Min-Hung Chen Yen-Yu Lin Yu-Lun Liu
CVPR 2025
project page / arXiv / code (coming soon) / huggingface

Developed a reference-guided 3D inpainting approach utilizing SDEdit on aligned Gaussian initialization, and created a 360° inpainting dataset (360-USID) for comprehensive evaluation.

FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors
Ching-Yang Lin*, Chung-Ho Wu*, Changhan Yeh, Alex Yen, Cheng Sun, Yu-Lun Liu
CVPR 2025
project page / arXiv / code (comming soon)

Utilizing self-guided adaptation of multi-scale voxel grid acheives fast convergence from sparse inputs.

Projects
Robot Navigation GIF
Intelligent Robot Navigation with Semantic Path Planning
NYCU CSIC30058: Perception and Decision Making in Intelligent Systems
2023-12-31
github /

A robot navigation system utilized 3D semantic reconstruction information with SLAM.

Water Seg
Boosting Zero-shot water segmentation
NYCU EEIE30068: Digital Image Processing (1st place in DIP water segmentation challenge)
2023-12-31
github /

Boosting CLIP-basde zero-shot text-prompt segmentation with fast bilateral solver.

Under The Lake: VR Horror Immersive Experience
NYCU CSIC30006: XR Camp (XR Showcase Silver Award)
2023-06-26
video /

VR horror immersive experience on scene captured from real campus.


Design and source code from Jon Barron's website.