Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟵𝟳 Computer Vision Learning 𝗧𝗲𝗱𝗶𝗚𝗔𝗡: Text-Guided Diverse Image Generation and Manipulation by Tsinghua Shenzhen International Graduate School, University College London, The Chinese University of Hong Kong and 深圳市大数据研究院 Shenzhen Research Institute of Big Data Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in #CVPR2021 with over 4 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/e88uRz6 Code: https://lnkd.in/e-3p5WF Colab : https://lnkd.in/e6GSAbF ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸  TediGAN, a novel framework for multi-modal image generation and manipulation with textual descriptions. The proposed method consists of three components: StyleGAN inversion module, visual-linguistic similarity learning, and instance-level optimization.  🔸 The inversion module maps real images to the latent space of a well-trained StyleGAN. The visual-linguistic similarity learns the text-image matching by mapping the image and text into a common embedding space. The instance-level optimization is for identity preservation in manipulation. Our model can produce diverse and high-quality images with an unprecedented resolution at 1024 x 1024. 🔸 Using a control mechanism based on style-mixing, our TediGAN inherently supports image synthesis with multi-modal inputs, such as sketches or semantic labels, with or without instance guidance. 🔸To facilitate text-guided multi-modal synthesis, we propose the Multi-Modal CelebA-HQ, a large-scale dataset consisting of real face images and corresponding semantic segmentation map, sketch, and textual descriptions. Extensive experiments on the introduced dataset demonstrate the superior performance of our proposed method.  #computervision #artificialintelligence #deeplearning