MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
Cheng-Han Lee,Ziwei Liu,Lingyun Wu,Ping Luo +3 more
- pp 5549-5558
Reads0
Chats0
TLDR
MaskGAN as mentioned in this paper proposes MaskGAN to enable diverse and interactive face manipulation by learning style mapping between a free-form user modified mask and a target image, enabling diverse generation results.Abstract:
Facial image manipulation has achieved great progress in recent years. However, previous methods either operate on a predefined set of face attributes or leave users little freedom to interactively manipulate images. To overcome these drawbacks, we propose a novel framework termed MaskGAN, enabling diverse and interactive face manipulation. Our key insight is that semantic masks serve as a suitable intermediate representation for flexible face manipulation with fidelity preservation. MaskGAN has two main components: 1) Dense Mapping Network (DMN) and 2) Editing Behavior Simulated Training (EBST). Specifically, DMN learns style mapping between a free-form user modified mask and a target image, enabling diverse generation results. EBST models the user editing behavior on the source mask, making the overall framework more robust to various manipulated inputs. Specifically, it introduces dual-editing consistency as the auxiliary supervision signal. To facilitate extensive studies, we construct a large-scale high-resolution face dataset with fine-grained mask annotations named CelebAMask-HQ. MaskGAN is comprehensively evaluated on two challenging tasks: attribute transfer and style copy, demonstrating superior performance over other state-of-the-art methods. The code, models, and dataset are available at https://github.com/switchablenorms/CelebAMask-HQ.read more
Citations
More filters
Proceedings ArticleDOI
Gradient Adjusting Networks for Domain Inversion
TL;DR: In this paper , a per-image optimization method that tunes a StyleGAN2 generator such that it achieves a local edit to the generator's weights, resulting in almost perfect inversion, while still allowing image editing, by keeping the rest of the mapping between an input latent representation tensor and an output image relatively intact.
Proceedings ArticleDOI
IFQA: Interpretable Face Quality Assessment
TL;DR: The authors proposed a face-centric metric based on an adversarial framework where a generator simulates face restoration and a discriminator assesses image quality, which can lead to performance improvement as an objective function.
Journal ArticleDOI
Effect of Instance Normalization on Fine-Grained Control for Sketch-Based Face Image Generation
Zhi-Quan Cheng,Xuejin Chen +1 more
TL;DR: This paper comprehensively investigate the effect of instance normalization on generating photorealistic face images from hand-drawn sketches and modifications in the baseline image translation model markedly improve the quality of synthesized images and the conformance with user intention.
Journal ArticleDOI
SUD2: Supervision by Denoising Diffusion Models for Image Reconstruction
TL;DR: In this paper , the authors propose a generalized framework for training image reconstruction networks when paired training data is scarce, and demonstrate the ability of image denoising algorithms and, by extension, denoizing diffusion models to supervise network training in the absence of paired data.
Book ChapterDOI
Improving Video Quality with Generative Adversarial Networks
TL;DR: In this article, deep learning methodologies that can be employed to recover image and video quality are discussed. Most of the covered approaches will be based on conditional Generative Adversarial Networks (GAN) which have the benefit to produce images which look more natural.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.