|
Gyeongsu Cho I am a Ph.D. student in Artificial Intelligence Graduate School at UNIST, where I am a 3D Vision & Robotics Lab member under Prof. Kyungdon Joo's supervision. I received a B.S. in Mechanical Engineering at Chung-Ang University.
I am actively seeking internship opportunities at academic or industrial research teams. |
|
ResearchI am passionate about creating models that don’t yet exist — models capable of reconstructing, animating, and generating dynamic 3D and 4D content, especially for humans and animals. My ultimate goal is to push the boundaries of dynamic 3D/4D reconstruction and generation. I'm driven by a passion for meaningful and enjoyable research, building tools and models that unlock new creative and scientific possibilities. |
 |
In submission We present a fast, pose-controllable 3D avatar generation framework from a single image. By combining facial identity and visual embeddings with pose-guided multi-view synthesis, our method creates high-fidelity, animation-ready human avatars in under 15 seconds. |
 |
Gyeongsu Cho, Changwoo Kang, Donghyeon Soon, Kyungdon Joo IJCV 2025, CV4Animals Oral (CVPRW 2024) We propose DogRecon, a novel framework that reconstructs animatable 3D Gaussian dog models from a single image. Our method leverages a canine prior and a reliable sampling strategy to produce high-quality 3D reconstructions and animations of dogs. |
 |
Jongsung Lee, Gyeognsu Cho*, Jeongin Park*, Kyongjun Kim*, Seongoh Lee*, Jung Hee Kim, Seong-Gyun Jeong, Kyungdon Joo ICCV 2023 SlaBins utilizes a slanted multi-cylindrical image representation and adaptive bins to generate accurate and dense depth maps. |
Education
|
Projects
|
|
Template from this website. |