Resultado de búsqueda
20 de jul. de 2022 · The official repo for CM-GAN (Cascaded Modulation GAN) for Image Inpainting. We introduce a new cascaded modulation design that cascades global modulation with spatial adaptive modulation for better hole filling.
22 de mar. de 2022 · CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training. Haitian Zheng, Zhe Lin, Jingwan Lu, Scott Cohen, Eli Shechtman, Connelly Barnes, Jianming Zhang, Ning Xu, Sohrab Amirghodsi, Jiebo Luo. Recent image inpainting methods have made great progress but often struggle to generate plausible image structures ...
InsetGAN — Official PyTorch implementation. InsetGAN for Full-Body Image Generation. Anna Frühstück, Krishna Kumar Singh, Eli Shechtman, Niloy Mitra, Peter Wonka, Jingwan Lu. published at CVPR 2022. Project Webpage. Abstract While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body ...
While GANs can produce photo-realistic images in ideal conditions for ... = {Fr\"uhst\"uck, Anna and Singh, Krishna Kumar and Shechtman, Eli and Mitra, Niloy J. and Wonka, Peter and Lu, Jingwan}, title = {InsetGAN for Full-Body Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern ...
22 de mar. de 2022 · A simple image inpainting baseline, Mobile Inpainting GAN (MI-GAN), which is approximately one order of magnitude computationally cheaper and smaller than existing state-of-the-art inpainting models, and can be efficiently deployed on mobile devices.
Instead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas.
Image Inpainting with Cascaded Modulation GAN and Object-Aware Training. Haitian Zheng1,2(B), Zhe Lin2, Jingwan Lu2, Scott Cohen2, Eli Shechtman2, Connelly Barnes2, Jianming Zhang2, Ning Xu2, Sohrab Amirghodsi2, and Jiebo Luo1. University of Rochester, Rochester, USA. Adobe Research, Bangalore, India.
