Cascaded network with deep intensity manipulation for scene understanding. (26th June 2019)

• Record Type: Journal Article
• Authors: Yang, Xin; Wang, Haoran; Chen, Shaozhe; Piao, Xinglin; Zhou, Dongsheng; Zhang, Qiang; Yin, Baocai; Wei, Xiaopeng
• Is Part Of: Computer animation and virtual worlds. Volume 30:Number 3/4(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-06-26
• Subjects: cascaded network -- DIMNet -- intensity manipulation -- low‐light -- scene understanding; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.1888
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: Scene understanding is essential to robotic navigation and autonomous driving as it provides semantic information to their controlling system. However, it will fail when processing low‐light images/videos captured under adverse weather or at night use state‐of‐the‐art scene understanding methods. A naive way to directly infer semantics from low‐light images is ill posed because the low‐light condition distorts pixel intensities and buries details. In order to address this problem, we propose the Deep Intensity Manipulation Network (DIMNet), which could relight the input images and recover the details, and combine the DIMNet with a scene understanding network to get a cascaded network to learn the semantics from low‐light images. Through learning pixel intensity manipulation, our method can generate images not only visually pleasing but also practical for scene understanding. Qualitative and quantitative experiments demonstrate that the proposed method is effective and robust for both synthetic and real‐world images. Abstract : In order to address low‐light scene understanding problem, we propose the Deep Intensity Manipulation network (DIMNet) which could re‐light the input images and recover the details, and combine the DIMNet with scene understanding network to get a cascaded network to learn the semantics from low‐light images.