2022-07-14 更新
Diverse Similarity Encoder for Deep GAN Inversion
Authors:Cheng Yu, Wenmin Wang
Current deep generative adversarial networks (GANs) can synthesize high-quality (HQ) images, so learning representation with GANs is favorable. GAN inversion is one of emerging approaches that study how to invert images into latent space. Existing GAN encoders can invert images on StyleGAN, but cannot adapt to other deep GANs. We propose a novel approach to address this issue. By evaluating diverse similarity in latent vectors and images, we design an adaptive encoder, named diverse similarity encoder (DSE), that can be expanded to a variety of state-of-the-art GANs. DSE makes GANs reconstruct higher fidelity images from HQ images, no matter whether they are synthesized or real images. DSE has unified convolutional blocks and adapts well to mainstream deep GANs, e.g., PGGAN, StyleGAN, and BigGAN.
PDF
点此查看论文截图
SD-GAN: Semantic Decomposition for Face Image Synthesis with Discrete Attribute
Authors:Zhou Kangneng, Zhu Xiaobin, Gao Daiheng, Lee Kai, Li Xinjie, Yin Xu-Cheng
Manipulating latent code in generative adversarial networks (GANs) for facial image synthesis mainly focuses on continuous attribute synthesis (e.g., age, pose and emotion), while discrete attribute synthesis (like face mask and eyeglasses) receives less attention. Directly applying existing works to facial discrete attributes may cause inaccurate results. In this work, we propose an innovative framework to tackle challenging facial discrete attribute synthesis via semantic decomposing, dubbed SD-GAN. To be concrete, we explicitly decompose the discrete attribute representation into two components, i.e. the semantic prior basis and offset latent representation. The semantic prior basis shows an initializing direction for manipulating face representation in the latent space. The offset latent presentation obtained by 3D-aware semantic fusion network is proposed to adjust prior basis. In addition, the fusion network integrates 3D embedding for better identity preservation and discrete attribute synthesis. The combination of prior basis and offset latent representation enable our method to synthesize photo-realistic face images with discrete attributes. Notably, we construct a large and valuable dataset MEGN (Face Mask and Eyeglasses images crawled from Google and Naver) for completing the lack of discrete attributes in the existing dataset. Extensive qualitative and quantitative experiments demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/MontaEllis/SD-GAN.
PDF 16 pages, 12 figures, Accepted by ACM MM2022
点此查看论文截图
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
Authors:Guohao Ying, Xin He, Bin Gao, Bo Han, Xiaowen Chu
Generative adversarial networks (GANs) have proven successful in image generation tasks. However, GAN training is inherently unstable. Although many works try to stabilize it by manually modifying GAN architecture, it requires much expertise. Neural architecture search (NAS) has become an attractive solution to search GANs automatically. The early NAS-GANs search only generators to reduce search complexity but lead to a sub-optimal GAN. Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training. To alleviate the instability, we propose an efficient two-stage evolutionary algorithm-based NAS framework to search GANs, namely EAGAN. We decouple the search of G and D into two stages, where stage-1 searches G with a fixed D and adopts the many-to-one training strategy, and stage-2 searches D with the optimal G found in stage-1 and adopts the one-to-one training and weight-resetting strategies to enhance the stability of GAN training. Both stages use the non-dominated sorting method to produce Pareto-front architectures under multiple objectives (e.g., model size, Inception Score (IS), and Fr\’echet Inception Distance (FID)). EAGAN is applied to the unconditional image generation task and can efficiently finish the search on the CIFAR-10 dataset in 1.2 GPU days. Our searched GANs achieve competitive results (IS=8.81$\pm$0.10, FID=9.91) on the CIFAR-10 dataset and surpass prior NAS-GANs on the STL-10 dataset (IS=10.44$\pm$0.087, FID=22.18). Source code: https://github.com/marsggbo/EAGAN.
PDF Accepted in ECCV2022, Guohao Yin and Xin He contributed equally
点此查看论文截图
Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs
Authors:Min Zhou, Chenchen Xu, Ye Ma, Tiezheng Ge, Yuning Jiang, Weiwei Xu
In this paper, we study the graphic layout generation problem of producing high-quality visual-textual presentation designs for given images. We note that image compositions, which contain not only global semantics but also spatial information, would largely affect layout results. Hence, we propose a deep generative model, dubbed as composition-aware graphic layout GAN (CGL-GAN), to synthesize layouts based on the global and spatial visual contents of input images. To obtain training images from images that already contain manually designed graphic layout data, previous work suggests masking design elements (e.g., texts and embellishments) as model inputs, which inevitably leaves hint of the ground truth. We study the misalignment between the training inputs (with hint masks) and test inputs (without masks), and design a novel domain alignment module (DAM) to narrow this gap. For training, we built a large-scale layout dataset which consists of 60,548 advertising posters with annotated layout information. To evaluate the generated layouts, we propose three novel metrics according to aesthetic intuitions. Through both quantitative and qualitative evaluations, we demonstrate that the proposed model can synthesize high-quality graphic layouts according to image compositions.
PDF Accepted by IJCAI 2022 (AI, THE ARTS AND CREATIVITY TRACK)
点此查看论文截图
RepMix: Representation Mixing for Robust Attribution of Synthesized Images
Authors:Tu Bui, Ning Yu, John Collomosse
Rapid advances in Generative Adversarial Networks (GANs) raise new challenges for image attribution; detecting whether an image is synthetic and, if so, determining which GAN architecture created it. Uniquely, we present a solution to this task capable of 1) matching images invariant to their semantic content; 2) robust to benign transformations (changes in quality, resolution, shape, etc.) commonly encountered as images are re-shared online. In order to formalize our research, a challenging benchmark, Attribution88, is collected for robust and practical image attribution. We then propose RepMix, our GAN fingerprinting technique based on representation mixing and a novel loss. We validate its capability of tracing the provenance of GAN-generated images invariant to the semantic content of the image and also robust to perturbations. We show our approach improves significantly from existing GAN fingerprinting works on both semantic generalization and robustness. Data and code are available at https://github.com/TuBui/image_attribution.
PDF Accepted at ECCV 2022; fix typo, add supmat
点此查看论文截图