Hwan Heo


Hello, I'm AI Researcher

About

Hi, it's a delightful serendipity to meet you in the vast expanse of the digital cosmos. I'm Hwan Heo (허환), a lifelong learner, and explorer in AI & 3D Computer Vision.

Vision AI Researcher

Specializing in 3D Computer Vision.

  • Interest: 3D Vision & Graphics AI
  • Degree: Master's in Computer Science
  • E-mail: gjghks950@naver.com
  • City: Sungnam, South Korea

Hwan Heo is an AI researcher at Graphics AI Lab, NC AI. He holds a B.S. and M.S. in Computer Science from Korea University, under the supervision of Professor Hyunwoo J. Kim. He was Research Intern in Generation Research at NAVER AI Lab mentored by Dr. Jin-Hwa Kim. His research emphasizes Computer Vision, Radiance Fields, and 3D Generation, contributing to the cutting-edge developments in these fascinating fields.

Summary

Hwan Heo | 허환

AI Researcher specializing in 3D Computer Vision with 3+ years of experience in developing cutting-edge techniques for Neural Rendering and 3D Generation.

  • AI Researcher at NC AI (NCSOFT)
  • Research Personnel, Alternative Military Service

Education

Master of Computer Science & Engineering

2020 - 2022

MLV Lab, Korea University, Seoul

Studied advanced machine learning, computer vision, generalization and related areas, building a theoretical and practical foundation.

Bachelor of Computer Science & Engineering

2015 - 2020

Korea University, Seoul

Gained a comprehensive understanding of computer science principles and engineering fundamentals through a rigorous undergraduate program.

Professional Experience

AI Researcher

2025 - Present

3D Generation, NC AI

  • Designed and developed core algorithms for Varco 3D, NC AI's flagship 3D generation service

AI Researcher

2023 - 2025

Neural Rendering & 3D Generation, NCSOFT Research

  • Led research and development of 3D asset generation, focusing on 3D Latent Diffusion and Texture Synthesis.
  • Developed and applied novel Neural Rendering solutions, including:
    • Integrating Gaussian Splatting into a proprietary game engine .
    • Creating a high-speed Neural Facial Avatar for multi-camera systems .

AI Researcher (Intern)

2022

Generation Research, NAVER AI Lab

  • Researched a novel Neural Rendering method using joint optimization of camera poses and hash grid radiance fields.

  • Image-to-Image Translation model specifically for equirectangular (360-degree) images.

Portfolio

Featured Publications & Projects
  • All
  • Research
  • Application
  • Personal


Publications

  • CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation

    Hwan Heo, Jangyeong Kim, Seongyeong Lee, Jeong-A Wi, Junyoung Choi, Sangjun Ahn
    Technical Report, Featured on HuggingFace's Daily Papers, TLDR AI

  • DreamSurfels: Generative Gaussian Surfels for Geometrically Accurate 3D Content Creation

    Hwan Heo, Sangjun Ahn
    The 15th International Conference on ICT Convergence (ICTC), Oct 2024
    Oral presentation, domestic conference

  • Robust Camera Pose Refinement for Multi-Resolution Hash Encoding

    Hwan Heo, Taekyung Kim, J. Lee, Jiyoung Lee, Soohyun Kim, Hyunwoo J. Kim, Jin-Hwa Kim
    The 40th International Conference on Machine Learning (ICML), Jul 2023

  • Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild

    Jaewon Lee, Injae Kim, Hwan Heo, Hyunwoo J. Kim
    preprint, arXiv 2023

  • Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

    Jihwan Park, Seunjun Lee, Hwan Heo, Hyunggyu Choi, Hyunwoo J. Kim
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2022

  • Domain Generalization Emerges from Dreaming

    Hwan Heo, Younjin Oh, Jaewon Lee, Hyunwoo J. Kim
    preprint, arXiv 2023

  • Temporally Sparse Adversarial Perturbations on Videos

    Hwan Heo, Dohwan Ko, Jaewon Lee, Youngjoon Hong, Hyunwoo J. Kim
    IEEE Access, Oct 2021 vol. 9, pp. 146938,
    Internatrional journal publication


Invited Talks

  • Radiance Fields and Spatial AI for Digital Twin

    National Geographic Information Institute in Korea (국토지리정보원), Oct 2025

  • Rasteriztion vs. Ray Tracing with 3D Gaussian Primitives

    NCSOFT Research, Sep 2024

  • Joint Optimization of Camera Pose and Accelerated Radiance Fields

    Naver Cloud, Mar 2023

Blog: link | velog (kor)

Featured Recent Posts: