[1905.10346] Mask-Guided Portrait Editing with Conditional GANs

Portrait editing is a popular subject in photo manipulation. The Generative Adversarial Network (GAN) advances the generating of realistic faces and allows more face editing. In this paper, we argue about three issues in existing techniques: diversity, quality, and controllability for portrait synthesis and editing. To address these issues, we propose a novel end-to-end learning framework that leverages conditional GANs guided by provided face masks for generating faces. The framework learns feature embeddings for every face component (e.g., mouth, hair, eye), separately, contributing to better correspondences for image translation, and local face editing. With the mask, our network is available to many applications, like face synthesis driven by mask, face Swap+ (including hair in swapping), and local manipulation. It can also boost the performance of face parsing a bit as an option of data augmentation.

1 mentions: @shion_honda
Keywords: gan
Date: 2019/11/08 11:20

Referring Tweets

@shion_honda Mask-Guided Portrait Editing [Gu+, 2019, CVPR] マスクからの顔画像生成、表情の変更、顔のパーツ交換など様々な操作が可能なGANモデルを提案。各パーツを埋め込むautoencoder、マスクに従ってパーツを並べるGen、ターゲットの背景に馴染ませるGenからなる。 t.co/1Ec4MRZHIw #NowReading t.co/vGTlqgFVKC

Related Entries

Read more Goodfellow先生おすすめのGAN論文6つを紹介
0 users, 0 mentions 2018/05/06 09:46
Read more Deep Learningを用いた教師なし画像検査の論文調査 GAN/SVM/Autoencoderとか .pdf
0 users, 0 mentions 2018/10/09 06:53
Read more GAN(と強化学習との関係)
23 users, 1 mentions 2019/04/04 17:16
Read more 敵対的生成ネットワーク(GAN)
67 users, 18 mentions 2019/02/25 12:47
Read more Icml2018読み会_overview&GANs
0 users, 0 mentions 2018/07/28 06:23