3D Vision, Robotics, and AI Research

I am a second-year Ph.D. student in Scalable Graphics, Vision, and Robotics (SGVR) Lab at KAIST, advised by Sung-Eui Yoon. Last Summer, I was fortunate to visit NAVER LABS Spatial AI team as a research intern. The goal of my research is to empower AI with spatial understanding by reconstructing, generating, and interacting within 3D scenes. Recently, I’ve been focusing on world models, robot vision, motion modeling, and rendering.

yjna2907 [at] kaist.ac.kr Daejeon, Korea 3D Vision • Robotics • AI

Publications

Selected publications. Full publication list, including domestic publications, is available in my CV.

  • GLINT preview

    GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport

    Youngju Na, Jaeseong Yun, Soohyun Ryu, Hyunsu Kim, Sung-Eui Yoon, and Suyong Yeon

    CVPR 2026 Oral

    Project Paper Code

  • Visual-RRT preview

    Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering

    Sebin Lee*, Jumin Lee*, Taeyeon Kim, Youngju Na, Woobin Im, and Sung-Eui Yoon

    CVPR 2026 Highlight

    Project Paper

  • MorphGS preview

    MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos

    Taeyeon Kim*, Youngju Na*, Jumin Lee, Sebin Lee, Minhyuk Sung, and Sung-eui Yoon

    arXiv 2026

    Project Paper

  • AegisRF preview

    AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields

    Woo Jae Kim, Kyu Beom Han, Yoonki Cho, Youngju Na, Junsik Jung, and Sung-eui Yoon

    BMVC 2025

    Project Paper Code

  • SHARE preview

    POSE-FREE 3D GAUSSIAN SPLATTING VIA SHAPE-RAY ESTIMATION

    Youngju Na*, Taeyeon Kim*, Jumin Lee, Kyu Beom Han, Woo Jae Kim, Sung-eui Yoon

    ICIP 2025 Best Student Paper Award (Top 0.16%)

    Paper Code

  • UFORecon preview

    UFORecon: generalizable sparse-view surface reconstruction from arbitrary and unfavorable sets

    Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, Sung-Eui Yoon

    CVPR 2024

    Project Paper Code

  • SKD preview

    Shared knowledge distillation for robust multi-scale super-resolution networks

    *Youngju Na, *Hee Hyeon Kim, Seok Bong Yoo

    Electronics Letters 2022

    Paper

  • HAZE-Net preview

    HAZE-Net: High-frequency attentive super-resolved gaze estimation in low-resolution face images

    Jun-Seok Yun, Youngju Na, Hee Hyeon Kim, Hyung-Il Kim, Seok Bong Yoo

    ACCV 2022

    Paper Code

  • LatentGaze preview

    Latentgaze: Cross-domain gaze estimation through gaze-aware analytic latent code manipulation

    Isack Lee, Jun-Seok Yun, Hee Hyeon Kim, Youngju Na, Seok Bong Yoo

    ACCV 2022

    Paper Code

Academic Activities

Reviewer

  • CVPR
  • ICCV
  • ICLR
  • NeurIPS
  • Transaction on Computational Imaging

Education

  • Ph.D in Computer Science, KAIST

    Mar. 2025 - current

  • Master's in Computer Science, KAIST

    Mar. 2023 - Feb 2025

  • B.S. in Industrial Engineering & IoT Artificial Intelligence, Chonnam National University

    Mar. 2017 - Feb. 2023

    Top Rank (GPA: 4.36 / 4.5, Major GPA: 4.46 / 4.5)

Teaching Experiences

  • Teaching Assistant, Data Structure (CS206), 2024 Fall, KAIST
  • Teaching Assistant, Computer Graphics (CS380), 2024 Spring, KAIST
  • Teaching Assistant, Introduction to Programming (CS101), 2023 Fall, KAIST
  • Teaching Assistant, Introduction to Algorithm (CS300), 2023 Spring, KAIST

Awards & Honors

  • Best Student Paper Award, ICIP 2025
  • 1st Prize, Harvest Festival Symposium, AI/IoT Section, CNU, 2022
  • 2nd Prize, Silicon Valley Innovation & Startup Program, San Jose university, 2021