Jungho Lee

I am a Ph.D candidate at Yonsei University in Seoul, where I work on computer vision and machine learning. Currently, I am a research intern at NAVER Cloud and participating in a Human Avatar Generation project.

My primary areas of research are 3D neural rendering for real-world scenarios and human avatar generation with 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF).

I'm always open to collaborations or suggestions. Please feel free to contact me if you have any questions or suggestions. :)

Email  /  CV  /  Google Scholar  /  Github  /  Linkedin

profile photo
Research
CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images
Jungho Lee, Donghyeong Kim, Dogyoon Lee, Suhwan Cho, Minhyeok Lee, Wonjoon Lee, Taeoh Kim, Dongyoon Wee, Sangyoun Lee
arXiv, 2025
project page / arXiv

We propose continous motion-aware blur kernel on 3D gaussian splatting utilizing 3D rigid transformation and neural ordinary differential function to reconstruct accurate 3D scene from blurry images with real-time rendering speed.

CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
Jungho Lee, Suhwan Cho, Taeoh Kim, Ho-Deok Jang, Minhyeok Lee, Geonho Cha, Dongyoon Wee, Dogyoon Lee, Sangyoun Lee
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2025
project page / arXiv

CoCoGaussian models the CoC at the 3D Gaussian level, reconstructing the precise 3D scene and enabling sharp novel view synthesis from defocused images.

Effective SAM Combination for Open-Vocabulary Semantic Segmentation
Minhyeok Lee, Suhwan Cho, Jungho Lee, Sunghun Yang, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2025
project page / arXiv

We propose a novel one-stage open-vocabulary semantic segmentation model, which effectively combines CLIP and SAM to leverage SAM’s powerful classagnostic segmentation capabilities while maintaining efficient inference.

Video Diffusion Models are Strong Video Inpainter
Minhyeok Lee, Suhwan Cho, Chajin Shin, Jungho Lee, Sunghun Yang, Sangyoun Lee
The Association for the Advancement of Artificial Intelligence (AAAI), 2025
project page / arXiv

We design a First Frame Filling Video Diffusion Inpainting model inspired by the capabilities of pre-trained image-to-video diffusion models that can transform the first frame image into a highly natural video.

Guided Slot Attention for Unsupervised Video Object Segmentation
Minhyeok Lee, Suhwan Cho, Dogyoon Lee, Chaewon Park, Jungho Lee, Sangyoun Lee
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2024
code / arXiv

We propose a guided slot attention network to reinforce spatial structural information and obtain better foreground–background separation.

Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
Jungho Lee, Minhyeok Lee, Dogyoon Lee, Sangyoun Lee
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
code / arXiv

We propose a hierarchically decomposed graph convolution with a novel hierarchically decomposed graph, which consider the sematic correlation between the joints and the edges of the human skeleton.

Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Jungho Lee, Minhyeok Lee, Suhwan Cho, Sungmin Woo, Sungjun Jang, Sangyoun Lee
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
code / arXiv

We propose a novel Spatio-Temporal Curve Network (STC-Net) for skeleton-based action recognition, which consists of spatial modules with an spatio-temporal curve (STC) module and graph convolution with dilated kernels (DK-GC)

Multi-Scale Structural Graph Convolutional Network for Skeleton-Based Action Recognition
Sungjun Jang, Heansung Lee, Woo Jin Kim, Jungho Lee, Sungmin Woo, Sangyoun Lee
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT)
paper

We propose the multi-scale structural graph convolutional network, the common intersection graph convolution leverages the overlapped neighbor information between neighboring vertices for a given pair of root vertices.


This website's source code is borrowed from Jon Barron's website template.

Last updated December 2024.