Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟳𝟰 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗥𝗲𝗮𝗹𝗶𝘀𝘁𝗶𝗰 𝗙𝘂𝗹𝗹-𝗕𝗼𝗱𝘆 𝗔𝗻𝗼𝗻𝘆𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗦𝘂𝗿𝗳𝗮𝗰𝗲-𝗚𝘂𝗶𝗱𝗲𝗱 𝗚𝗔𝗡𝘀 𝗯𝘆 𝗡𝗼𝗿𝘄𝗲𝗴𝗶𝗮𝗻 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝘆 𝗼𝗳 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗮𝗻𝗱 𝗧𝗲𝗰𝗵𝗻𝗼𝗹𝗼𝗴𝘆 Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: 𝗙𝘂𝗹𝗹-𝗕𝗼𝗱𝘆 𝗔𝗻𝗼𝗻𝘆𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗦𝘂𝗿𝗳𝗮𝗰𝗲-𝗚𝘂𝗶𝗱𝗲𝗱 𝗚𝗔𝗡𝘀 🔸 This paper is published arxiv2021. 🔸 Present a novel full-body anonymization framework that generates-to-photorealistic and diverse humans in varying and complex scenes. Experiments show that guiding adversarial nets with dense pixel-to-surface correspondences strongly improves the synthesis of high-fidelity textures for varying poses and scenes. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Recent work on image anonymization has shown that generative adversarial networks (GANs) can generate near-photorealistic faces to anonymize individuals. 🔸 🔸 However, scaling these networks to the entire human body has remained a challenging and yet unsolved task.  🔸 We propose a new anonymization method that generates close-to-photorealistic humans for in-the-wild images. 🔸 A key part of our design is to guide adversarial nets by dense pixel-to-surface correspondences between an image and a canonical 3D surface. 🔸 We introduce Variational Surface-Adaptive Modulation (V-SAM) that embeds surface information throughout the generator. 🔸 Combining this with our novel discriminator surface supervision loss, the generator can synthesize high-quality humans with diverse appearances in complex and varying scenes. 🔸 We show that surface guidance significantly improves image quality and diversity of samples, yielding a highly practical generator. 🔸 Finally, we demonstrate that surface-guided anonymization preserves the usability of data for future computer vision development. #computervision #artificialintelligence #gan