首页|Findings in Computational Intelligence Reported from China University of Mining and Technology Beijing (Joint Self-supervised Enhancement and Denoising of Low-l ight Images)
Findings in Computational Intelligence Reported from China University of Mining and Technology Beijing (Joint Self-supervised Enhancement and Denoising of Low-l ight Images)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing-Computational Intelligence have been published. According to news reportin g from Beijing, People's Republic of China, by NewsRx journalists, research stat ed, "Images taken under low-light conditions often suffer from multiple degradat ions such as low visibility and unknown noise. Low-light image enhancement is an important task in the field of computer vision." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news correspondents obtained a quote from the research from the China Univer sity of Mining and Technology Beijing, "In order to avoid the limited number of samples in paired datasets, several self-supervised enhancement methods have bee n developed. However, due to the designed illumination gradient prior, most self -supervised enhancement methods based on Retinex cannot effectively constrain th e illumination or suppress the amplified real noise. To solve this problem, this paper explores a joint self-supervised enhancement and denoising method for low -light image. Initially, we proposed a new regularization term, named TV-Huber, and developed an adaptive illumination estimation network (AIENet) to explore t he intrinsic relationship between structure and texture in the illumination map. Next, the camera response model and the learned illumination are then used to e nhance the contrast of low-light images and mitigate color shifts. Finally, the learned illumination maps are transformed into illumination masks. Under the ass umption of independent and zero-mean noise, selective feature injection is perfo rmed on the shallow features extracted by the blind-spot network (BSN) to reduce information loss while removing unknown real noise in the dark area."
BeijingPeople's Republic of ChinaAsi aComputational IntelligenceMachine LearningChina University of Mining and Technology Beijing
NETL
NSTL
