While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. Instead of modeling this complex domain with a single GAN, we propo...
InsetGAN FullBodyImageGenerationCVPR2022 发布于 2022-03-18 23:15 · 894 次播放 赞同1添加评论 分享收藏喜欢 举报 学术论文CVPR2022生成对抗网络(GAN)增强现实(AR)行人重识别 写下你的评论... 还没有评论,发表第一个评论吧 相关推荐 8:14 中国企业出手,美国ai泡沫开始出现裂缝...
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 AbstractWhile GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human...