Doctoral student at ETH Zürich

hohs [at] ethz.ch
azuxmioy [at] gmail.com

CV

Twitter

Linkedin

GitHub


Bio

I am a third-year PhD student supervised by Prof. Dr. Otmar Hilliges. I obtained my Computer Science Master's degree at ETH Zürich in 2021. My research interests lie in human-centric computer vision ranging from basic understandings of human-centric videos, such as human recognition and pose estimation, to more complicated generative tasks, such as motion prediction and full-body generation. Recently, I am interested in leveraging generative 3D avatars to facilitate human pose estimation and 3D understanding.

Photo took in Kobe, Japan. 2016

Education


Master of Science in Computer Science,
ETH Zürich

[September.2018 - June.2021]


Bachelor of Science in Electrical Engineering,
National Taiwan University

[September.2012 - June.2016]



Practical Experience

Publications

teaser figure

SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

Hsuan-I Ho, Jie Song, Otmar Hilliges

[CVPR 2024 (BibTeX)] [Supplementary] [Project Page] [Code] [Video]

teaser figure

4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations

Wenbo Wang*, Hsuan-I Ho*, Chen Guo, Boxiang Rong, Artur Grigorev, Jie Song, Juan Jose Zarate, Otmar Hilliges

(* indicates equal contribution.)

[CVPR 2024 Highlight (BibTeX)] [Supplementary] [Project Page] [Code] [Video]

teaser figure

Learning Locally Editable Virtual Humans

Hsuan-I Ho, Lixin Xue, Jie Song, Otmar Hilliges

[CVPR 2023 (BibTeX)] [Supplementary] [Project Page] [Code] [Video]

teaser figure

Render In-between: Motion Guided Video Synthesis for Action Interpolation

Hsuan-I Ho, Xu Chen, Jie Song, Otmar Hilliges

[BMVC 2021 (BibTeX)] [Supplementary] [Code]

teaser figure

READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification

Minho Shim, Hsuan-I Ho, Jinhyung Kim Dongyoon Wee

[ECCV 2020 (BibTeX)] [Code]

teaser figure

Learning from Dances: Pose-Invariant Re-Identification for Multi-Person Tracking

Hsuan-I Ho, Minho Shim, Dongyoon Wee

[ICASSP 2020 (BibTeX)] [Dataset] [Code] [Demo]

teaser figure

Summarizing First-Person Videos from Third Persons’ Points of View

Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang

[ECCV 2018 (BibTeX)] [Supplementary] [Project Page]

teaser figure

A Benchmark Dataset for 6DoF Object Pose Tracking

Po-Chen Wu, Yueh-Ying Lee*, Hung-Yu Tseng*, Hsuan-I Ho*, Ming-Hsuan Yang, Shao-Yi Chien

(* indicates equal contribution.)

[ISMAR 2017 (BibTeX)] [Project Page]






Selected Works

Course Projects

teaser figure

Motion Guided Human Video Synthesis

Hsuan-I Ho, Xu Chen, Jie Song, Otmar Hilliges

Master's thesis

[Master Thesis (BibTeX)]

teaser figure

Supe®oad: Road Segmentation through Multi-objective Ensemble and Geometric-aware Post-processing

Davin Choo, Hsuan-I Ho, Juan-Ting Lin, Vaclav Rozhon

(Names are in alphabetical order of first names.)

Computational Intelligence Lab course project at ETH Zürich

[Project Report] [Project Page]

teaser figure

Neural Network Adversarial Attack Analysis

Hsuan-I Ho, Chi-Ching Hsu

Reliable and Interpretable Artificial Intelligence course project at ETH Zürich

[Project Report] [Code]


Copyright © 2017 Husan-I Ho
Special Thanks : Walon Chiu provides his template
(Last Modified: 1st.5.2022)