Jiin Im

Jiin Im

Research Assistant @ Spatial AI Lab, Hanyang University

About

I am a Research Assistant (previously Master's student) at the Spatial AI Lab, Hanyang University, advised by Prof. Je Hyeong Hong. My research interests lie in computer vision and computer graphics, with a focus on correspondence and spatial reasoning.

I am particularly interested in how correspondence can serve as a foundation for spatial reasoning, where the goal is to discover meaningful part-level relationships across objects, views, and modalities. My interests span both image-level and shape-level correspondence, including spectral approaches to matching across 3D geometries, and how these can be connected so that agents reason over spatial structure in a viewpoint-invariant manner.

This direction is motivated by real-world perception problems where appearance alone is insufficient: recognizing that two visually different objects share the same functional part, or generalizing manipulation skills across unseen environments. I believe spatial understanding grounded in correspondence is a key building block for such capabilities.

I am actively seeking Ph.D. opportunities starting in Fall 2027. If you are interested in discussing my research or potential collaborations, I'd love to grab a coffee at CVPR 2026 in Denver or chat over email! ☕

Education

Hanyang University Mar. 2026 - Present

Research Assistant (Advisor: Je Hyeong Hong)

Hanyang University Mar. 2024 - Feb. 2026

M.S. in Electronic Engineering (Advisor: Je Hyeong Hong)

Hanyang University Mar. 2020 - Feb. 2024

B.S. in Electronic Engineering, Summa Cum Laude

Publications

Shape-of-You Teaser Image

Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild

Jiin Im, Sisung Liu, Je Hyeong Hong

CVPR 2026

Paper Code
FUN-AD Teaser Image

FUN-AD: Fully Unsupervised Learning for Anomaly Detection with Noisy Training Data

Jiin Im*, Yongho Son*, Je Hyeong Hong

WACV 2025

Paper Code

Projects

Semantic Correspondence via Structural Information on 2D and 3D Domains Mar. 2025 - Present

Establishing semantic correspondence on both 2D image and 3D geometry domains using structural information, which is related to Shape-of-You.

Non-Rigid Registration of Deformed Point Clouds via Geometric Correspondence Jun. 2025 - Dec. 2025

Focused on estimating geometric correspondence in deformed point clouds to perform robust non-rigid registration.

Privacy-Preserving Geometric Description against Image Reconstruction Jun. 2024 - Feb. 2025

Explored geometric description methods that prevent original image recovery from descriptors while maintaining matching performance.

Unsupervised Anomaly Detection with Noisy Training Data Jan. 2023 - May. 2024

Addressing anomaly detection in unsupervised settings with noisy training data related to FUN-AD.

Experience

Hobbies

In my free time, I enjoy:

Contact

✉️ Email: skqldit33@hanyang.ac.kr

📍 Location: Engineering Center Annex Unit 415-1, Hanyang University, Seongdong-gu, Wangsimni-ro 222, Seoul, South Korea