Yonwoo Choi

Algorithm Engineer
GenGenAI
Email: yhugestar-at-gmail-dot-com

Google Scholar CV OpenReview GitHub LinkedIn

I am currently fulfilling my alternative military service as an Algorithm Engineer at GenGenAI, where I work on 3D-based synthetic data generation, working closely with Suhwan Cho.

My research lies in 3D computer vision centered on humans, with a focus on capturing, understanding, and reconstructing people in 3D. Ultimately, I aim to build machines that perceive and understand human motion and behavior as naturally as people understand one another. I pursue this direction by building practical capture systems and learning-based methods that bring humans into the digital world.

I completed my M.S. at Seoul National University and my B.A. at the University of Virginia, both in computer science. During my M.S., I was fortunate to be part of the Visual Computing Lab under the supervision of Hanbyul Joo. Previously, I have worked at SECERN AI, working on Animatable 3D Human Avatars.

• Sep 2025I started working as an Algorithm Engineer at GenGenAI.
• Mar 2025SVAD has been accepted to CVPR 2025 Workshop SyntaGen.
• Mar 2024I started working as a Research Engineer at SECERN AI.
• Feb 2024I've graduated from SNU with an M.S.

• 
  SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation

  Yonwoo Choi

  CVPR 2025 Workshop, SyntaGen — Harnessing Generative Models for Synthetic Visual Datasets, 2025

  Paper Project Page Code arXiv Review
• 
  A Wrist Mounted Camera System for Hand Pose Estimation from Single RGB Images

  Yonwoo Choi, Hanbyul Joo

  Master's Thesis, Computer Science and Engineering, Seoul National University, 2024

  Paper PDF

• 
  Single Image to 3D Human Avatar

  SECERN AI, May 2025

  - Official Implementation of the paper SVAD
  - Synthetic Data Generation Pipeline for 3DGS Avatar Training

  Code
• 
  Facebuilder

  SECERN AI, March 2025

  - 3D Face Mesh Deformation with Pin-Based Interaction
  - Multiview Face Modeling with Real-time 3D Consistency

  Code
• 
  Multiview X-Ray 3D Object Detector

  SECERN AI, December 2024

  - 9-view Fanbeam Calibration
  - X-Ray Hazardous Objection Detection
  - 3D Bounding Box Detection

  Code
• 
  SMPL Fitting

  SECERN AI, June 2024

  - Fitting SMPL Parameters to 3D Human Joints
  - Parametric Human Shape and Pose Optimization

  Code
• 
  Egocentric Human Pose Estimator

  Visual Computing Lab, December 2023

  - Unofficial Implementation of the Paper xR-EgoPose
  - Egocentric 3D Human Pose Estimation from a Single Fisheye Camera

  Code
• 
  Multiview Human Pose Capture System

  Visual Computing Lab, April 2022

  - 5 GoPro Camera Setup for 3D Human Reconstruction
  - Camera Calibration with Zhang's Method

  Code

• 
  GenGenAI

  Algorithm Engineer, September 2025 – Present

  - Controllable Image and Video Generation Across Domains
• 
  SECERN AI

  Research Engineer, March 2024 – September 2025

  - Animatable 3D Human Avatars

• Fall 2023Teaching Assistant, Seoul National University — 4190.408 001 Artificial Intelligence (Instructor: Hanbyul Joo)
• Spring 2022Teaching Assistant, Seoul National University — 4190.773 002 3D Computer Vision (Instructor: Hanbyul Joo)