Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟵𝟵 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Auto-Exposure Fusion for Single-Image Shadow Removal by University of South Carolina, USA Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in #CVPR2021 with over 5 citations. 🔸 It outperforms JIGen, BigAug, Epi-FCR, RSC ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eUnbx8b Code : https://lnkd.in/exdzRP8 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Shadow removal is still a challenging task due to its inherent background dependent and spatial-variant properties, leading to unknown and diverse shadow patterns. Even powerful deep neural networks could hardly recover trace- less shadow-removed background. 🔸 This paper proposes a new solution for this task by formulating it as an exposure fusion problem to address the challenges. Intuitively, we can first estimate multiple over-exposure images w.r.t. the input image to let the shadow regions in these images have the same color with shadow-free areas in the input image. 🔸 Then, we fuse the original input with the over-exposure images to generate the final shadow-free counterpart. Nevertheless, the spatial-variant property of the shadow requires the fusion to be sufficiently `smart', that is, it should automatically select proper over-exposure pixels from different images to make the final output natural. 🔸 To address this challenge, we propose the shadow-aware FusionNet that takes the shadow image as input to generate fusion weight maps across all the over-exposure images. Moreover, we propose the boundary-aware RefineNet to eliminate the remaining shadow trace further. We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods. #computervision #artificialintelligence #data