In-Young Cho Email & Phone Number

South Korea

San Francisco, Ca, Us

대한민국 서울

• Implemented a scalable 2D texture dataset construction algorithm that processes 70K unstructured 3D assets within a day, and developed diffusion models using ControlNet and LoRA, enabling physically-based texture generation on consumer devices.• Reduced the execution time of an algorithm for converting unstructured meshes into watertight meshes by 1/10000 by lowering the time complexity and utilizing multiprocessing, improving the 3D mesh generation model’s quality.• Optimized a… Show more • Implemented a scalable 2D texture dataset construction algorithm that processes 70K unstructured 3D assets within a day, and developed diffusion models using ControlNet and LoRA, enabling physically-based texture generation on consumer devices.• Reduced the execution time of an algorithm for converting unstructured meshes into watertight meshes by 1/10000 by lowering the time complexity and utilizing multiprocessing, improving the 3D mesh generation model’s quality.• Optimized a large-scale 3D reconstruction model, enabling game assets to be generated from a single photo in under 30 seconds on consumer devices, garnering attention as the top AI innovation in the upcoming flagship game. Show less

대한민국 서울

• Designed and deployed Point Transformer-based reinforcement learning algorithms (A3C, PPO) to optimize building designs, enhancing profit maximization while adhering to regulations.• Applied pairwise ranking learning for reward function tuning, reducing tuning time by 200x and increasing agreement with architect preferences from 55% to 90%, doubling AI outputs meeting human-quality standards to 60%.

대전

Provided academic and career counseling for 50 undergraduate students, supporting their decision-making and personal growth.

대한민국 대전

Assisted the introduction to computer graphics course (CS380).

Developed a multi-view line retrieval system for 3D indoor scene reconstruction, applying view frustum culling, epipolar geometry, and 2D line detection and matching.

Seoul, Republic Of Korea

Developed a deep learning model for breast cancer diagnosis in whole-slide images of tera-pixels.

Master Of Science - Ms, Computer Science, 4.25/4.30

- Advisor: Prof. Sung-Eui Yoon - Thesis: Deep Light Clustering for Denoising Monte Carlo Renderings - Research area: physically-based.

Bachelor'S Degree, Computer Science & Mathematical Science (Double), 4.00/4.30

Activities and Societies: Handcrafting club and korean archery club - Honors: summa cum laude, dean's list (top 3%) - Coursework: computer.

Summer Session, Software Science, 3.85/4.00 (4.14/4.30)

CMPM 80K: FoundationsGameDesgn CMPS 115: Intro Software Eng

Education record

Activities and Societies: Orchestra club (violin)