https://scholar.dgist.ac.kr/handle/20.500.11750/4354 Sat, 04 Apr 2026 07:42:00 GMT 2026-04-04T07:42:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/11697 Title: Locally Adaptive Channel Attention-Based Network for Denoising Images Author(s): Lee, Haeyun; Cho, Sunghyun Abstract: Channel attention has recently been proposed and shown a great improvement in image classification accuracy. In this paper, we show that channel attention can greatly help a low-level vision task, image denoising, as well, and propose channel attention-based networks for image denoising. We provide a thorough analysis on the effect of channel attention on image denoising, which shows that channel attention boosts denoising performance by making the network to focus on informative channels more closely related to noise. We also show that channel attention has an adaptive nature to image contents and noise and propose locally adaptive channel attention for further improving image denoising quality. Experimental results show that our denoising network with global channel attention outperforms existing state-of-the-art methods in both blind and non-blind settings, and our locally adaptive channel attention substantially improves both image quality and computation time. © 2013 IEEE. Fri, 31 Jan 2020 15:00:00 GMT https://scholar.dgist.ac.kr/handle/20.500.11750/11697 2020-01-31T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/10395 Title: Interactive and Automatic Navigation for 360 degrees Video Playback Author(s): Kang, Kyoungkook; Cho, Sunghyun Abstract: A common way to view a 360? video on a 2D display is to crop and render a part of the video as a normal field-of-view (NFoV) video. While users can enjoy natural-looking NFoV videos using this approach, they need to constantly make manual adjustment of the viewing direction not to miss interesting events in the video. In this paper, we propose an interactive and automatic navigation system for comfortable 360? video playback. Our system finds a virtual camera path that shows the most salient areas through the video, generates a NFoV video based on the path, and plays it in an online manner. A user can interactively change the viewing direction while watching a video, and the system instantly updates the path reflecting the intention of the user. To enable online processing, we design our system consisting of an offline pre-processing step, and an online 360? video navigation step. The pre-processing step computes optical flow and saliency scores for an input video. Based on these, the online video navigation step computes an optimal camera path reflecting user interaction, and plays a NFoV video in an online manner. For improved user experience, we also introduce optical flow-based camera path planning, saliency-aware path update, and adaptive control of the temporal window size. Our experimental results including user studies show that our system provides more pleasant experience of watching 360? videos than existing approaches. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM. Sun, 30 Jun 2019 15:00:00 GMT https://scholar.dgist.ac.kr/handle/20.500.11750/10395 2019-06-30T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/10272 Title: 적응형 채널 어텐션 모듈을 활용한 복합 열화 복원 네트워크 Author(s): 이해윤; 조성현 Abstract: 자율 주행 자동차나 소방 로봇과 같은 시스템에서 영상을 얻을 때 다양한 요인들로 인해 잡음，블러와 같은 열화가 발생한 다. 이런 열화된 영상에 직접 영상 분류와 같은 기술을 적용하기 어려워 열화 제거가 불가피하나 이러한 시스템들은 영상의 열화를 인식할 수 없어서 열화된 영상을 복원하는데 어려움이 있다. 본 논문에서는 영상에 적용된 열화를 인지하지 못하는 상황에서 여러 방법들로 열화된 영상으로부터 자연스럽고 선명한 영상을 복원하는 방법을 제안한다. 우리가 제안한 방법은 딥러닝 모델에 채널 어텐션 모듈과스깁 커넥션을사용하여 영상에 적용된 열화에 따라복원에 필요한 채널에 높은 가중치를 적용해 복합 열화 영상의 복원을 진행한다. 이 방법은 다른복합 열화복원 방법 에 비해 학습이 간단하고 기존의 다른 방법들에 비 해 높은 복합 열화 복원 성능을 낸다. The image obtained from systems such as autonomous driving cars or fire-fighting robots often suffer from several degradation such as noise, motion blur, and compression artifact due to multiple factor. It is difficult to apply image recognition to these degraded images, then the image restoration is essential. However, these systems cannot recognize what kind of degradation and thus there are difficulty restoring the images. In this paper, we propose the deep neural network, which restore natural images from images degraded in several ways such as noise, blur and JPEG compression in situations where the distortion applied to images is not recognized. We adopt the channel attention modules and skip connections in the proposed method, which makes the network focus on valuable information to image restoration. The proposed method is simpler to train than other methods, and experimental results show that the proposed method outperforms existing state-of-the-art methods. Sun, 30 Jun 2019 15:00:00 GMT https://scholar.dgist.ac.kr/handle/20.500.11750/10272 2019-06-30T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/9333 Title: Deblurring Low-Light Images with Light Streaks Author(s): Hu, Zhe; Cho, Sunghyun; Wang, Jue; Yang, Ming-Hsuan Abstract: Images acquired in low-light conditions with handheld cameras are often blurry, so steady poses and long exposure time are required to alleviate this problem. Although significant advances have been made in image deblurring, state-of-the-art approaches often fail on low-light images, as a sufficient number of salient features cannot be extracted for blur kernel estimation. On the other hand, light streaks are common phenomena in low-light images that have not been extensively explored in existing approaches. In this work, we propose an algorithm that utilizes light streaks to facilitate deblurring low-light images. The light streaks, which commonly exist in the low-light blurry images, contain rich information regarding camera motion and blur kernels. A method is developed in this work to detect light streaks for kernel estimation. We introduce a non-linear blur model that explicitly takes light streaks and corresponding light sources into account, and pose them as constraints for estimating the blur kernel in an optimization framework. For practical applications, the proposed algorithm is extended to handle images undergoing non-uniform blur. Experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods on deblurring real-world low-light images. © 2018 IEEE. Sun, 30 Sep 2018 15:00:00 GMT https://scholar.dgist.ac.kr/handle/20.500.11750/9333 2018-09-30T15:00:00Z