Deep generative models, like GANs, have considerably improved the state of the art in image synthesis, and are able to generate near photo-realistic images in structured domains such as human faces. Based on this success, recent work on image editing proceeds by projecting images to the GAN latent space and manipulating the latent vector. However, these approaches are limited in that only images from a narrow domain can be transformed, and with only a limited number of editing operations. We propose FlexIT, a novel method which can take any input image and a user-defined text instruction for editing. Our method achieves flexible and natural editing, pushing the limits of semantic image translation. First, FlexIT combines the input image and text into a single target point in the CLIP multimodal embedding space. Via the latent space of an auto-encoder, we iteratively transform the input image toward the target point, ensuring coherence and quality with a variety of novel regularization terms. We propose an evaluation protocol for semantic image translation, and thoroughly evaluate our method on ImageNet. Code will be made publicly available.
Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis
University of Science and Technology of China（中国科学技术大学）；Suzhou Institute of Biomedical Engineering and Technology（苏州生物医学工程与技术研究所）；Chinese Academy of Sciences（中国科学院）；The Third Affiliated Hospital of Sun Yat-sen University（中山大学第三附属医院）
Diffusion models are able to generate photorealistic images in arbitrary scenes. However, when applying diffusion models to image translation, there exists a trade-off between maintaining spatial structure and high-quality content. Besides, existing methods are mainly based on test-time optimization or fine-tuning model for each input image, which are extremely time-consuming for practical applications. To address these issues, we propose a new approach for flexible image translation by learning a layout-aware image condition together with a text condition. Specifically, our method co-encodes …
Image-to-image (I2I) translation is usually carried out among discrete domains. However, image domains, often corresponding to a physical value, are usually continuous. In other words, images gradually change with the value, and there exists no obvious gap between different domains. This paper intends to build the model for I2I translation among continuous varying domains. We first divide the whole domain coverage into discrete intervals, and explicitly model the latent style code for the center of each interval. To deal with continuous translation, we design the editing modules, changing the …
Korea Advanced Institute of Science & Technology (KAIST)（韩国高等科学技术研究院（KAIST））
One of the important research topics in image generative models is to disentangle the spatial contents and styles for their separate control. Although StyleGAN can generate content feature vectors from random noises, the resulting spatial content control is primarily intended for minor spatial variations, and the disentanglement of global content and styles is by no means complete. Inspired by a mathematical understanding of normalization and attention, here we present a novel hierarchical adaptive Diagonal spatial ATtention (DAT) layers to separately manipulate the spatial contents from style…
Guangdong University of Technology（广东工业大学）；The University of Sydney（悉尼大学）
Unpaired image-to-image translation aims to find a mapping between the source domain and the target domain. To alleviate the problem of the lack of supervised labels for the source images, cycle-consistency based methods have been proposed for image structure preservation by assuming a reversible relationship between unpaired images. However, this assumption only uses limited correspondence between image pairs. Recently, contrastive learning (CL) has been used to further investigate the image correspondence in unpaired image translation by using patch-based positive/negative learning. Patch-ba…
Northwestern Polytechnical University（西北工业大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Data-driven paradigms using machine learning are becoming ubiquitous in image processing and communications. In particular, image-to-image (I2I) translation is a generic and widely used approach to image processing problems, such as image synthesis, style transfer, and image restoration. At the same time, neural image compression has emerged as a data-driven alternative to traditional coding approaches in visual communications. In this paper, we study the combination of these two paradigms into a joint I2I compression and translation framework, focusing on multi-domain image synthesis. We firs…
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（南方科技大学可信自主系统研究院）；Southern University of Science and Technology（南方科技大学）；School of Electrical and Electronic Engineering, Huazhong University of Science and Technology（华中科技大学电气与电子工程学院）；Huazhong University of Science and Technology（华中科技大学）
Despite significant advances in image-to-image (I2I) translation with generative adversarial networks (GANs), it remains challenging to effectively translate an image to a set of diverse images in multiple target domains using a single pair of generator and discriminator. Existing I2I translation methods adopt multiple domain-specific content encoders for different domains, where each domain-specific content encoder is trained with images from the same domain only. Nevertheless, we argue that the content (domain-invariance) features should be learned from images among all of the domains. Conse…
Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
Score-based diffusion models (SBDMs) have achieved the SOTA FID results in unpaired image-to-image translation (I2I). However, we notice that existing methods totally ignore the training data in the source domain, leading to sub-optimal solutions for unpaired I2I. To this end, we propose energy-guided stochastic differential equations (EGSDE) that employs an energy function pretrained on both the source and target domains to guide the inference process of a pretrained SDE for realistic and faithful unpaired I2I. Building upon two feature extractors, we carefully design the energy function such…
Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is often difficult to maintain the original content of the image during the reverse diffusion. To address this, here we present a novel diffusion-based unsupervised image translation method using disentangled style and content representation. Specifically, inspired by the splicing Vision Transformer, we extract intermediate keys of multihead self attention layer f…
Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Generative Adversarial Networks (GANs) with style-based generators (e.g. StyleGAN) successfully enable semantic control over image synthesis, and recent studies have also revealed that interpretable image translations could be obtained by modifying the latent code. However, in terms of the low-level image content, traveling in the latent space would lead to `spatially entangled changes' in corresponding images, which is undesirable in many real-world applications where local editing is required. To solve this problem, we analyze properties of the 'style space' and explore the possibility of co…
Harbin Institute of Technology（哈尔滨工业大学）；Baidu Inc.（百度公司）；Peng Cheng Laboratory（鹏城实验室）
Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks. However, the bottleneck layer in encoder-decoder usually gives rise to blurry and low quality editing result. And adding skip connections improves image quality at the cost of weakened attribute manipulation ability. Moreover, existing methods exploit target attribute vector to guide the flexible translation to desired target domain. In this work, we suggest to address these issues from selective transfer perspective. Considering that specific editing task is certainly onl…
Nanyang Technological University（南洋理工大学）；Alibaba Group（阿里巴巴集团）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
We develop a new method for portrait image editing, which supports fine-grained editing of geometries, colors, lights and shadows using a single neural network model. We adopt a novel asymmetric conditional GAN architecture: the generators take the transformed conditional inputs, such as edge maps, color palette, sliders and masks, that can be directly edited by the user; the discriminators take the conditional inputs in the way that can guide controllable image generation more effectively. Taking color editing as an example, we feed color palettes (which can be edited easily) into the generat…
Department of Health Technology and Informatics, Hong Kong Polytechnic University（香港理工大学健康科技与信息技术系）；Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）；Department of Biomedical Engineering, The Johns Hopkins University（约翰霍普金斯大学生物医学工程系）
Shanghai Key Laboratory of Multidimensional Information Processing（上海多维度信息处理重点实验室）；Huazhong University of Science and Technology（华中科技大学）
Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion and editing model for pretrained StyleGAN which is not only with less distortions, but also of high quality and flexibility for editing. The proposed model employs a CNN encoder to provide multi-scale image features as keys and values. Meanwhile it regards the style code to be determined for different layers of the generator as queries. It first initializes query tokens as learnable parameters and maps them into W+ …
Event cameras are novel sensors that perceive the per-pixel intensity changes and output asynchronous event streams with high dynamic range and less motion blur. It has been shown that events alone can be used for end-task learning, e.g., semantic segmentation, based on encoder-decoder-like networks. However, as events are sparse and mostly reflect edge information, it is difficult to recover original details merely relying on the decoder. Moreover, most methods resort to pixel-wise loss alone for supervision, which might be insufficient to fully exploit the visual details from sparse events, …
Image translation methods typically aim to manipulate a set of labeled attributes (given as supervision at training time e.g. domain label) while leaving the unlabeled attributes intact. Current methods achieve either: (i) disentanglement, which exhibits low visual fidelity and can only be satisfied where the attributes are perfectly uncorrelated. (ii) visually-plausible translations, which are clearly not disentangled. In this work, we propose OverLORD, a single framework for disentangling labeled and unlabeled attributes as well as synthesizing high-fidelity images, which is composed of two …
Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Qi Zhi Institute（上海期智研究院）
The diagnosis of cancer is mainly performed by visual analysis of the pathologists, through examining the morphology of the tissue slices and the spatial arrangement of the cells. If the microscopic image of a specimen is not stained, it will look colorless and textured. Therefore, chemical staining is required to create contrast and help identify specific tissue components. During tissue preparation due to differences in chemicals, scanners, cutting thicknesses, and laboratory protocols, similar tissues are usually varied significantly in appearance. This diversity in staining, in addition to…
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial examples, raising concerns about the robustness of such systems. Adversarial examples that are not restricted to small perturbations could be more serious since conventional certified defenses might be ineffective against them. To shed light on the vulnerability to such adversarial examples, we propose a flexible and efficient method for generating unrestricted…
