Dogyoon Lee

I am a research engineer at Samsung Research in Seoul, South Korea.

My research mainly focuses on various 2D/3D computer vision tasks including generative models, neural rendering, and image/video enhancement.

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

profile photo
Selected Publication
ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
Sungmin Woo*, Wonjoon Lee*, Woojin Kim, Dogyoon Lee, Sangyoun Lee
European Conference on Computer Vision (ECCV) , 2024
Project Page / Paper / Code

We propose novel cost volume refinement model for self-supervised multi-frame monocular depth estimation model.

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
Paper / Code / bib

We propose a guided slot attention network to reinforce spatial structural information and obtain better foregroundā€“background separation.

Dual Prototype Attention for Unsupervised Video Object Segmentation
Suhwan Cho, Minhyeok Lee, Seunghoon Lee, Dogyoon Lee, Sangyoun Lee
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2024
Paper / Code / bib

We propose two novel prototype-based attention mechanisms to incorporate different modalities and frames via dense propagation across them.

DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors
Dogyoon Lee, Minhyeok Lee, Chajin Shin, Sangyoun Lee
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2023
Project Page / Paper / Code / bib

We impose the physical constraints on the blurring kernel of neural radiance field to construct clean neural radiance field from blurry images.

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
Paper / Code / bib

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.

TSANET: Temporal and Scale Alignment for Unsupervised Video Object Segmentation
Seunghoon Lee, Suhwan Cho, Dogyoon Lee, Minhyeok Lee, Sangyoun Lee
IEEE International Conference on Image Processing (ICIP), 2023
Paper / bib

We propose a novel framework for unsupervised video object segmentation, which can utilize both contextual and motion information from adjacent frames, introducing a temporal and scale alignment network (TSANet).

Mkconv: Multidimensional Feature Representation for Point Cloud Analysis
Sungmin Woo, Dogyoon Lee, Sangwon Hwang, Woojin Kim, Sangyoun Lee
Pattern Recognition (PR), 2023
Paper / bib

We propose a novel framework for point cloud processing, which can utilize both local and global information from point clouds, introducing a multidimensional feature representation (Mkconv).

Expanded Adaptive Scaling Normalization for End-to-End Image Compression
Chajin Shin, Hyeongmin Lee, Hanbin Son, Sangjin Lee, Dogyoon Lee, Sangyoun Lee
European Conference on Computer Vision (ECCV), 2022
Paper / Code / bib

We propose rescaling module for the image compression network which is enhanced version of existing GDN with higher degree of freedom.

Robust Lane Detection via Expanded Self attention
Minhyeok Lee, Junhyeop Lee, Dogyoon Lee, Woojin Kim, Sangwon Hwang, Sangyoun Lee
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022
Paper / Code / bib

We propose a novel self-attention module called the Expanded Self Attention for lane detection in autonomous vehicle to be robust in challenging situations.

Regularization Strategy for Point Cloud via Rigidly Mixed Sample
Dogyoon Lee, Jaeha Lee, Junhyeop Lee, Hyeongmin Lee, Minhyeok Lee, Sungmin Woo, Sangyoun Lee
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2021
Paper / Code / bib

We propose a novel data augmentation method called Rigid Subset Mix (RSMix) which generates virtual mixed samples by replacing part of the sample with shape-preserved subsets from another sample.

False Positive Removal For 3D Vehicle Detection with Penetrated Point Classifier
Sungmin Woo, Sangwon Hwang, Woojin Kim, Junhyeop Lee, Dogyoon Lee, Sangyoun Lee
IEEE International Conference on Image Processing (ICIP), 2020
Paper / bib

We propose a novel post-processing method to remove false positives in 3D vehicle detection utilizing the characteristics of the LiDAR censor itself.

Preprint
Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation
Minhyeok Lee, Dogyoon Lee, Jungho Lee, Suhwan Cho, Heeseung Choi, Ig-jae Kim, Sangyoun Lee
Arxiv, Preprint, Pending, 2024
Paper / Code / bib

We propose novel bi-directional token-masking autoencoder (BTMAE) for referring image segmentation (RIS) to effectively utilize contextual information between language and visual features.

Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse View
Dogyoon Lee, Donghyeong Kim, Jungho Lee, Minhyeok Lee, Seunghoon Lee, Sangyoun Lee
Arxiv, Preprint, Pending, 2024
Project Page / Paper

We propose enhanced deblurred neural radiance fields from sparse view settings for more practical applications considering real-world scenarios.

SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields
Jungho Lee, Dogyoon Lee, Minhyeok Lee, Donghyeong Kim Sangyoun Lee
Arxiv, Preprint, Pending, 2024
Paper / Code / bib

We propose novel blur kernel for motion estimation based on neural ordinary differential function to construct the deblurred neural radiance fields.

CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion Blur Images
Jungho Lee, Donghyeong Kim, Dogyoon Lee, Suhwan Cho, Sangyoun Lee
Arxiv, Preprint, Pending, 2024
Project Page / Paper / Code

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.


This website's source code is borrowed from jonbarron's website.

Last updated September 2024.