Papers of the day   All papers

Self-Supervised Scene De-occlusion

Comments

Goku Mohandas: ๐Ÿคฏ This recent work by @ccloy et al. blew my mind: Self-Supervised Scene De-occlusion (CVPR 2020) - https://arxiv.org/abs/2004.02788 Check out media/questions that Xiaohang (first author) has been answering on @madewithml: https://madewithml.com/@xiaohangzhan/details/168/self-supervised-scene-de-occlusion/ https://t.co/CWXDFREFpR

10 replies, 1077 likes


Ziwei Liu: Our #CVPR2020 **oral** paper "Self-Supervised Scene De-occlusion": Paper: https://arxiv.org/pdf/2004.02788.pdf Code: https://github.com/XiaohangZhan/deocclusion/ Demo: https://www.youtube.com/watch?v=xIHCyyaB5gU - A self-supervised framework that can recover occluded objects & their spatial orders from a single RGB image. https://t.co/CaKbJ4aoS5

0 replies, 219 likes


Chen Change Loy: Thanks @GokuMohandas for sharing our work! We already released the code at https://github.com/XiaohangZhan/deocclusion

0 replies, 99 likes


Insane: Self-Supervised Scene De-occlusion (CVPR 2020) Read More: https://arxiv.org/abs/2004.02788 Cc: @jblefevre60 @gp_pulipaka @fchollet @chipro @sallyeaves @FrRonconi @ingliguori @daviddegroof1 @PatrickGunz_CH @hwingo @ipfconline1 @TechNative @_TechMode @kcgcse @Ronald_vanLoon @grattonboy https://t.co/g3se7l0Syb

1 replies, 15 likes


๐•Š๐•–๐•ฃ๐•˜ ๐•„๐•’๐•ครญ๐•ค ๐Ÿงข๐Ÿ“ˆ: #MachineLearning Wizardry! ๐Ÿง™โ€โ™‚๏ธ #AI #PyTorch

1 replies, 2 likes


akira: https://arxiv.org/abs/2004.02788 PCNets for self-supervised learning that complements the hidden parts of objects by adding individual order. By covering the image with other objects taken at random, the system learns to generate masks and complete the hidden parts. https://t.co/UDL08IrZhu

0 replies, 1 likes


Content

Found on Apr 07 2020 at https://arxiv.org/pdf/2004.02788.pdf

PDF content of a computer science paper: Self-Supervised Scene De-occlusion