Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Rim, Jaesung"'
Autor:
Kim, Sanghyun, Lee, Min Jung, Kim, Woohyeok, Jung, Deunsol, Rim, Jaesung, Cho, Sunghyun, Cho, Minsu
Burst image super-resolution has been a topic of active research in recent years due to its ability to obtain a high-resolution image by using complementary information between multiple frames in the burst. In this work, we explore using burst shots
Externí odkaz:
http://arxiv.org/abs/2406.17869
In this paper, we present GyroDeblurNet, a novel single image deblurring method that utilizes a gyro sensor to effectively resolve the ill-posedness of image deblurring. The gyro sensor provides valuable information about camera motion during exposur
Externí odkaz:
http://arxiv.org/abs/2404.00916
Mobile cameras, despite their significant advancements, still have difficulty in low-light imaging due to compact sensors and lenses, leading to longer exposures and motion blur. Traditional blind deconvolution methods and learning-based deblurring m
Externí odkaz:
http://arxiv.org/abs/2312.13317
We present ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization. Our approach consists of two main components: 6-DOF camera trajectory-based motion blur formulation and voxel-based r
Externí odkaz:
http://arxiv.org/abs/2309.08957
Autor:
Lee, Sohyun, Rim, Jaesung, Jeong, Boseung, Kim, Geonu, Woo, Byungju, Lee, Haechan, Cho, Sunghyun, Kwak, Suha
We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality significantly. To add
Externí odkaz:
http://arxiv.org/abs/2303.15410
Training learning-based deblurring methods demands a tremendous amount of blurred and sharp image pairs. Unfortunately, existing synthetic datasets are not realistic enough, and deblurring models trained on them cannot handle real blurred images effe
Externí odkaz:
http://arxiv.org/abs/2202.08771
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 2034-2042
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) that is specifically designed to handle spatially-varying and large def
Externí odkaz:
http://arxiv.org/abs/2108.13610