KunHo Heo

About Me

I am a MS student in Computer Engineering at Kyung Hee University, advised by Prof. MyeongAh Cho. My research focuses on 3D Computer Vision and Robotics Applications, particularly human motion and human–scene interaction.

If you have a moment, click the icon below to explore my homepage through an interactive 3D scene.

News

[Sep. 2026] One paper got accepted at NeurIPS 2026.
[Jun. 2026] One paper got accepted at ECCV 2026.
[Feb. 2026] One paper got accepted at CVPR 2026.
[Sep. 2025] One paper got accepted at NeurIPS 2025.
[Mar. 2025] Joined as an M.S. student at Visual Science Lab, Kyung Hee University.

Publications

NeurIPS

Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling

KunHo Heo*, SuYeon Kim*, Hayoung Lee, Chanse Oh, MyeongAh Cho

The Conference on Neural Information Processing Systems (NeurIPS), 2026

Paper Code Project

ECCV

Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection

KunHo Heo*, Seungjae Kim*, Wongyu Lee*, SuYeon Kim, MyeongAh Cho

European Conference on Computer Vision (ECCV), 2026

Paper Code Project

CVPR

ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis

KunHo Heo, SuYeon Kim, Yonghyun Gwon, Youngbin Kim, MyeongAh Cho

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Paper Code Project

NeurIPS

Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction

KunHo Heo*, GiHyun Kim*, SuYeon Kim, MyeongAh Cho

The Conference on Neural Information Processing Systems (NeurIPS), 2025

Paper Code Project