Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟭𝟬 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗛𝗶𝘀𝘁𝗼𝗚𝗔𝗡: Controlling Colors of GAN-Generated and Real Images via Color Histograms, Brown York University Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in CVPR2021 with over 1 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eDMEHCN Code : https://lnkd.in/eKsVB4N ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸While generative adversarial networks (GANs) can successfully produce high-quality images, they can be challenging to control. Simplifying GAN-based image generation is critical for their adoption in graphic design and artistic work. 🔸  This goal has led to significant interest in methods that can intuitively control the appearance of images generated by GANs. In this paper, we present HistoGAN11, a color histogram-based method for controlling GAN-generated images’ colors.  🔸 We focus on color histograms as they provide an intuitive way to describe image color while remaining decoupled from domain-specific semantics. Specifically, we introduce an effective modification of the recent StyleGAN architecture to control the colors of GAN-generated images specified by a target color histogram feature. 🔸We then describe how to expand HistoGAN to recolor real images. For image recoloring, we jointly train an encoder network along with HistoGAN. The recoloring model, ReHistoGAN, is an unsupervised approach trained to encourage the network to keep the original image’s content while changing the colors based on the given target histogram.  🔸 We show that this histogram-based approach offers a better way to control GAN-generated and real images’ colors while producing more compelling results compared to existing alternative strategies. #computervision #artificialintelligence #deeplearning