2023-01-26 更新
BallGAN: 3D-aware Image Synthesis with a Spherical Background
Authors:Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun, Youngjung Uh
3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images, they suffer from unstable training or degenerate solutions where the 3D geometry is unnatural. We hypothesize that the 3D geometry is underdetermined due to the insufficient constraint, i.e., being classified as real image to the discriminator is not enough. To solve this problem, we propose to approximate the background as a spherical surface and represent a scene as a union of the foreground placed in the sphere and the thin spherical background. It reduces the degree of freedom in the background field. Accordingly, we modify the volume rendering equation and incorporate dedicated constraints to design a novel 3D-aware GAN framework named BallGAN. BallGAN has multiple advantages as follows. 1) It produces more reasonable 3D geometry; the images of a scene across different viewpoints have better photometric consistency and fidelity than the state-of-the-art methods. 2) The training becomes much more stable. 3) The foreground can be separately rendered on top of different arbitrary backgrounds.
PDF Project Page: https://minjung-s.github.io/ballgan
点此查看论文截图
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
Authors:Axel Sauer, Tero Karras, Samuli Laine, Andreas Geiger, Timo Aila
Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. However, the best-performing models require iterative evaluation to generate a single sample. In contrast, generative adversarial networks (GANs) only need a single forward pass. They are thus much faster, but they currently remain far behind the state-of-the-art in large-scale text-to-image synthesis. This paper aims to identify the necessary steps to regain competitiveness. Our proposed model, StyleGAN-T, addresses the specific requirements of large-scale text-to-image synthesis, such as large capacity, stable training on diverse datasets, strong text alignment, and controllable variation vs. text alignment tradeoff. StyleGAN-T significantly improves over previous GANs and outperforms distilled diffusion models - the previous state-of-the-art in fast text-to-image synthesis - in terms of sample quality and speed.
PDF Project page: https://sites.google.com/view/stylegan-t/
点此查看论文截图
DIFAI: Diverse Facial Inpainting using StyleGAN Inversion
Authors:Dongsik Yoon, Jeong-gi Kwak, Yuanming Li, David Han, Hanseok Ko
Image inpainting is an old problem in computer vision that restores occluded regions and completes damaged images. In the case of facial image inpainting, most of the methods generate only one result for each masked image, even though there are other reasonable possibilities. To prevent any potential biases and unnatural constraints stemming from generating only one image, we propose a novel framework for diverse facial inpainting exploiting the embedding space of StyleGAN. Our framework employs pSp encoder and SeFa algorithm to identify semantic components of the StyleGAN embeddings and feed them into our proposed SPARN decoder that adopts region normalization for plausible inpainting. We demonstrate that our proposed method outperforms several state-of-the-art methods.
PDF ICIP 2022
点此查看论文截图
CADA-GAN: Context-Aware GAN with Data Augmentation
Authors:Sofie Daniels, Jiugeng Sun, Jiaqing Xie
Current child face generators are restricted by the limited size of the available datasets. In addition, feature selection can prove to be a significant challenge, especially due to the large amount of features that need to be trained for. To manage these problems, we proposed CADA-GAN, a \textbf{C}ontext-\textbf{A}ware GAN that allows optimal feature extraction, with added robustness from additional \textbf{D}ata \textbf{A}ugmentation. CADA-GAN is adapted from the popular StyleGAN2-Ada model, with attention on augmentation and segmentation of the parent images. The model has the lowest \textit{Mean Squared Error Loss} (MSEloss) on latent feature representations and the generated child image is robust compared with the one that generated from baseline models.
PDF Submitted to ETHDL2023
点此查看论文截图
Interpreting CNN Predictions using Conditional Generative Adversarial Networks
Authors:Akash Guna R T, Raul Benitez, Sikha O K
We propose a novel method that trains a conditional Generative Adversarial Network (GAN) to generate visual interpretations of a Convolutional Neural Network (CNN). To comprehend a CNN, the GAN is trained with information on how the CNN processes an image when making predictions. Supplying that information has two main challenges: how to represent this information in a form that is feedable to the GANs and how to effectively feed the representation to the GAN. To address these issues, we developed a suitable representation of CNN architectures by cumulatively averaging intermediate interpretation maps. We also propose two alternative approaches to feed the representations to the GAN and to choose an effective training strategy. Our approach learned the general aspects of CNNs and was agnostic to datasets and CNN architectures. The study includes both qualitative and quantitative evaluations and compares the proposed GANs with state-of-the-art approaches. We found that the initial layers of CNNs and final layers are equally crucial for interpreting CNNs upon interpreting the proposed GAN. We believe training a GAN to interpret CNNs would open doors for improved interpretations by leveraging fast-paced deep learning advancements. The code used for experimentation is publicly available at https://github.com/Akash-guna/Explain-CNN-With-GANS
PDF Article submitted to JMLR. 19 Pages
点此查看论文截图
Towards Arbitrary Text-driven Image Manipulation via Space Alignment
Authors:Yunpeng Bai, Zihan Zhong, Chao Dong, Weichen Zhang, Guowei Xu, Chun Yuan
The recent GAN inversion methods have been able to successfully invert the real image input to the corresponding editable latent code in StyleGAN. By combining with the language-vision model (CLIP), some text-driven image manipulation methods are proposed. However, these methods require extra costs to perform optimization for a certain image or a new attribute editing mode. To achieve a more efficient editing method, we propose a new Text-driven image Manipulation framework via Space Alignment (TMSA). The Space Alignment module aims to align the same semantic regions in CLIP and StyleGAN spaces. Then, the text input can be directly accessed into the StyleGAN space and be used to find the semantic shift according to the text description. The framework can support arbitrary image editing mode without additional cost. Our work provides the user with an interface to control the attributes of a given image according to text input and get the result in real time. Ex tensive experiments demonstrate our superior performance over prior works.
PDF 8 pages, 12 figures
点此查看论文截图
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
Authors:Shizun Wang, Weihong Zeng, Xu Wang, Hao Yang, Li Chen, Chuang Zhang, Ming Wu, Yi Yuan, Yunzhao Zeng, Min Zheng
The creation of a parameterized stylized character involves careful selection of numerous parameters, also known as the “avatar vectors” that can be interpreted by the avatar engine. Existing unsupervised avatar vector estimation methods that auto-create avatars for users, however, often fail to work because of the domain gap between realistic faces and stylized avatar images. To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works. SwiftAvatar introduces dual-domain generators to create pairs of realistic faces and avatar images using shared latent codes. The latent codes can then be bridged with the avatar vectors as pairs, by performing GAN inversion on the avatar images rendered from the engine using avatar vectors. Through this way, we are able to synthesize paired data in high-quality as many as possible, consisting of avatar vectors and their corresponding realistic faces. We also propose semantic augmentation to improve the diversity of synthesis. Finally, a light-weight avatar vector estimator is trained on the synthetic pairs to implement efficient auto-creation. Our experiments demonstrate the effectiveness and efficiency of SwiftAvatar on two different avatar engines. The superiority and advantageous flexibility of SwiftAvatar are also verified in both subjective and objective evaluations.
PDF
点此查看论文截图
Improving Sketch Colorization using Adversarial Segmentation Consistency
Authors:Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
We propose a new method for producing color images from sketches. Current solutions in sketch colorization either necessitate additional user instruction or are restricted to the “paired” translation strategy. We leverage semantic image segmentation from a general-purpose panoptic segmentation network to generate an additional adversarial loss function. The proposed loss function is compatible with any GAN model. Our method is not restricted to datasets with segmentation labels and can be applied to unpaired translation tasks as well. Using qualitative, and quantitative analysis, and based on a user study, we demonstrate the efficacy of our method on four distinct image datasets. On the FID metric, our model improves the baseline by up to 35 points. Our code, pretrained models, scripts to produce newly introduced datasets and corresponding sketch images are available at https://github.com/giddyyupp/AdvSegLoss.
PDF Under review at Pattern Recognition Letters. arXiv admin note: substantial text overlap with arXiv:2102.06192
点此查看论文截图