181 citations · 274 across the 6 of their papers we have counts for
6 papers · 1 filter
SparseVoxFormer: Sparse Voxel-based Transformer for Multi-modal 3D Object Detection
Hyeongseok Son, Jia He, Seung-In Park +3
Most previous 3D object detection methods that leverage the multi-modality of LiDAR and cameras utilize the Bird's Eye View (BEV) space for intermediate feature representation. How…
Object-Centric Multi-Task Learning for Human Instances
Hyeongseok Son, Sangil Jung, Solae Lee +3
Human is one of the most essential classes in visual recognition tasks such as detection, segmentation, and pose estimation. Although much effort has been put into individual tasks…
Real-Time Video Deblurring via Lightweight Motion Compensation
Hyeongseok Son, Junyong Lee, Sunghyun Cho +1
While motion compensation greatly improves video deblurring quality, separately performing motion compensation and video deblurring demands huge computational overhead. This paper…
Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes
Hyeongseok Son, Junyong Lee, Jonghyeop Lee +2
For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation betwee…
Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions
Hyeongseok Son, Junyong Lee, Sunghyun Cho +1
This paper proposes a novel deep learning approach for single image defocus deblurring based on inverse kernels. In a defocused image, the blur shapes are similar among pixels alth…
Iterative Filter Adaptive Network for Single Image Defocus Deblurring
Junyong Lee, Hyeongseok Son, Jaesung Rim +2
We propose a novel end-to-end learning-based approach for single image defocus deblurring. The proposed approach is equipped with a novel Iterative Filter Adaptive Network (IFAN) t…