We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is suboptimal as the normalization layers tend to ``wash away'' semantic information. To address the issue, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned transformation. Experiments on several challenging datasets demonstrate the advantage of the proposed method over existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows user control over both semantic and style. Code is available at https://github.com/NVlabs/SPADE .
Image synthesis learns a transformation from the intensity features of an input image to yield a different tissue contrast of the output image. This process has been shown to have application in many medical image analysis tasks including imputation, registration, and segmentation. To carry out synthesis, the intensities of the input images are typically scaled--i.e., normalized--both in training to learn the transformation and in testing when applying the transformation, but it is not presently known what type of input scaling is optimal. In this paper, we consider seven different intensity n…
Tomorrow Advancing Life（好未来）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）
Semantic image synthesis is a challenging task with many practical applications. Albeit remarkable progress has been made in semantic image synthesis with spatially-adaptive normalization and existing methods normalize the feature activations under the coarse-level guidance (e.g., semantic class). However, different parts of a semantic object (e.g., wheel and window of car) are quite different in structures and textures, making blurry synthesis results usually inevitable due to the missing of fine-grained guidance. In this paper, we propose a novel normalization module, termed as REtrieval-bas…
Controllable person image generation aims to produce realistic human images with desirable attributes such as a given pose, cloth textures, or hairstyles. However, the large spatial misalignment between source and target images makes the standard image-to-image translation architectures unsuitable for this task. Most state-of-the-art methods focus on alignment for global pose-transfer tasks. However, they fail to deal with region-specific texture-transfer tasks, especially for person images with complex textures. To solve this problem, we propose a novel Spatially-Adaptive Warped Normalization…
Existing deep neural networks for histopathology image synthesis cannot generate image styles that align with different organs, and cannot produce accurate boundaries of clustered nuclei. To address these issues, we propose a style-guided instance-adaptive normalization (SIAN) approach to synthesize realistic color distributions and textures for histopathology images from different organs. SIAN contains four phases, semantization, stylization, instantiation, and modulation. The first two phases synthesize image semantics and styles by using semantic maps and learned image style vectors. The in…
University of Science and Technology of China（中国科学技术大学）；Microsoft Cloud AI（微软云人工智能）；Snap Inc.（Snap公司）；City University of Hong Kong（香港城市大学）；University of Southern California（南加利福尼亚大学）
Spatially-adaptive normalization is remarkably successful recently in conditional semantic image synthesis, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to preserve the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the true advantages inside the box is still highly demanded, to help reduce the significant computation and parameter overheads introduced by these new structures. In this paper, from a return-on-investment point of view, we present a deep analysis o…
We propose semantic region-adaptive normalization (SEAN), a simple but effective building block for Generative Adversarial Networks conditioned on segmentation masks that describe the semantic regions in the desired output image. Using SEAN normalization, we can build a network architecture that can control the style of each semantic region individually, e.g., we can specify one style reference image per region. SEAN is better suited to encode, transfer, and synthesize style than the best previous method in terms of reconstruction quality, variability, and visual quality. We evaluate SEAN on m…
University of Science and Technology of China（中国科学技术大学）；Microsoft Cloud AI（微软云AI）；Snap Inc.（Snap公司）；City University of Hong Kong（香港城市大学）；USC Institute for Creative Technologies（南加州大学创意技术研究所）；Wormpex AI Research LLC（Wormpex AI研究有限责任公司）
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away. Despite its impressive performance, a more thorough understanding of the advantages inside the box is still highly demanded to help reduce the significant computation and parameter overhead introduced by this novel structure. In this paper, from a return-on-investment point of view, we c…
The University of Tokyo（东京大学）；Preferred Networks, Inc.（Preferred Networks公司）
We present a novel CNN-based image editing strategy that allows the user to change the semantic information of an image over an arbitrary region by manipulating the feature-space representation of the image in a trained GAN model. We will present two variants of our strategy: (1) spatial conditional batch normalization (sCBN), a type of conditional batch normalization with user-specifiable spatial weight maps, and (2) feature-blending, a method of directly modifying the intermediate features. Our methods can be used to edit both artificial image and real image, and they both can be used togeth…
Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh. Particularly in this paper, we are interested in transferring the pose of source human mesh to deform the target human mesh, while the source and target meshes may have different identity information. Traditional studies assume that the paired source and target meshes are existed with the point-wise correspondences of user annotated landmarks/mesh points, which requires heavy labelling efforts. On the other hand, the generalization ability of deep models is limited, when the source and t…
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention (MHSA) in the Transformer model so powerful, this paper proposes to extend the widely adopted light-weight Squeeze-Excitation (SE) module to be spatially-adaptive to reinforce its data specificity, as a convolutional alternative of the MHSA, while retaining the efficiency of SE and the inductive basis of convolution. It presents two designs of spatially-adapt…
Artistic style transfer aims to transfer the style characteristics of one image onto another image while retaining its content. Existing approaches commonly leverage various normalization techniques, although these face limitations in adequately transferring diverse textures to different spatial locations. Self-Attention-based approaches have tackled this issue with partial success but suffer from unwanted artifacts. Motivated by these observations, this paper aims to combine the best of both worlds: self-attention and normalization. That yields a new plug-and-play module that we name Self-Att…
Text-to-image synthesis aims to generate natural images conditioned on text descriptions. The main difficulty of this task lies in effectively fusing text information into the image synthesis process. Existing methods usually adaptively fuse suitable text information into the synthesis process with multiple isolated fusion blocks (e.g., Conditional Batch Normalization and Instance Normalization). However, isolated fusion blocks not only conflict with each other but also increase the difficulty of training (see first page of the supplementary). To address these issues, we propose a Recurrent Af…
Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative model for high-quality and controllable scene synthesis. The key ingredient of our method is a very abstract object-level representation (i.e., 3D bounding boxes without semantic annotation) as the scene layout prior, which is simple to obtain, general to describe various scene contents, and yet informative to disentangle objects and background. Moreover, it s…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Style transfer is the image synthesis task, which applies a style of one image to another while preserving the content. In statistical methods, the adaptive instance normalization (AdaIN) whitens the source images and applies the style of target images through normalizing the mean and variance of features. However, computing feature statistics for each instance would neglect the inherent relationship between features, so it is hard to learn global styles while fitting to the individual training dataset. In this paper, we present a novel learnable normalization technique for style transfer usin…
The Seoul Institute（首尔研究院）；Sandia National Laboratories（桑迪亚国家实验室）；University of Hawai’i at Mānoa（夏威夷大学马诺阿分校）
The earth texture with complex morphological geometry and compositions such as shale and carbonate rocks, is typically characterized with sparse field samples because of an expensive and time-consuming characterization process. Accordingly, generating arbitrary large size of the geological texture with similar topological structures at a low computation cost has become one of the key tasks for realistic geomaterial reconstruction. Recently, generative adversarial neural networks (GANs) have demonstrated a potential of synthesizing input textural images and creating equiprobable geomaterial ima…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Yandex；University of Oxford（牛津大学）
The recent work of Gatys et al., who characterized the style of an image by the statistics of convolutional neural network filters, ignited a renewed interest in the texture generation and image stylization problems. While their image generation technique uses a slow optimization process, recently several authors have proposed to learn generator neural networks that can produce similar outputs in one quick forward pass. While generator networks are promising, they are still inferior in visual quality and diversity compared to generation-by-optimization. In this work, we advance them in two sig…
Person image synthesis, e.g., pose transfer, is a challenging problem due to large variation and occlusion. Existing methods have difficulties predicting reasonable invisible regions and fail to decouple the shape and style of clothing, which limits their applications on person image editing. In this paper, we propose PISE, a novel two-stage generative model for Person Image Synthesis and Editing, which is able to generate realistic person images with desired poses, textures, or semantic layouts. For human pose transfer, we first synthesize a human parsing map aligned with the target pose to r…
Image generation has raised tremendous attention in both academic and industrial areas, especially for the conditional and target-oriented image generation, such as criminal portrait and fashion design. Although the current studies have achieved preliminary results along this direction, they always focus on class labels as the condition where spatial contents are randomly generated from latent vectors. Edge details are usually blurred since spatial information is difficult to preserve. In light of this, we propose a novel Spatially Constrained Generative Adversarial Network (SCGAN), which deco…
In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies between regions according to their appearance correlation, yielding both spatially variant and associated representations. Conditioning on these features, we propose a dynamic weighted network constructed by spatially conditional computation (with both convolution and normalization). More than preserving semantic distinctions, the given dynamic network strengthe…
With the remarkable recent progress on learning deep generative models, it becomes increasingly interesting to develop models for controllable image synthesis from reconfigurable inputs. This paper focuses on a recent emerged task, layout-to-image, to learn generative models that are capable of synthesizing photo-realistic images from spatial layout (i.e., object bounding boxes configured in an image lattice) and style (i.e., structural and appearance variations encoded by latent vectors). This paper first proposes an intuitive paradigm for the task, layout-to-mask-to-image, to learn to unfold…
University of Science and Technology of China（中国科学技术大学）；Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
With the rapid development of the Metaverse, virtual humans have emerged, and human image synthesis and editing techniques, such as pose transfer, have recently become popular. Most of the existing techniques rely on GANs, which can generate good human images even with large variants and occlusions. But from our best knowledge, the existing state-of-the-art method still has the following problems: the first is that the rendering effect of the synthetic image is not realistic, such as poor rendering of some regions. And the second is that the training of GAN is unstable and slow to converge, su…
Normalization layers and activation functions are fundamental components in deep networks and typically co-locate with each other. Here we propose to design them using an automated approach. Instead of designing them separately, we unify them into a single tensor-to-tensor computation graph, and evolve its structure starting from basic mathematical functions. Examples of such mathematical functions are addition, multiplication and statistical moments. The use of low-level mathematical functions, in contrast to the use of high-level modules in mainstream NAS, leads to a highly sparse and large …
Guangdong Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）
Though GAN (Generative Adversarial Networks) based technique has greatly advanced the performance of image synthesis and face translation, only few works available in literature provide region based style encoding and translation. We propose in this paper a region-wise normalization framework, for region level face translation. While per-region style is encoded using available approach, we build a so called RIN (region-wise normalization) block to individually inject the styles into per-region feature maps and then fuse them for following convolution and upsampling. Both shape and texture of d…
The goal of semantic image synthesis is to generate photo-realistic images from semantic label maps. It is highly relevant for tasks like content generation and image editing. Current state-of-the-art approaches, however, still struggle to generate realistic objects in images at various scales. In particular, small objects tend to fade away and large objects are often generated as collages of patches. In order to address this issue, we propose a Dual Pyramid Generative Adversarial Network (DP-GAN) that learns the conditioning of spatially-adaptive normalization blocks at all scales jointly, su…
Northwestern University（西北大学）；University of Rochester（罗切斯特大学）
We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to regular. We adopt StyleGAN3 for synthesis and demonstrate that it produces diverse textures beyond those represented in the training data. For texture analysis, we propose GAN inversion using a novel latent domain reconstruction consistency criterion for synthesized textures, and iterative refinement with Gramian loss for real textures. We propose perceptual pro…
RATLIP: Generative Adversarial CLIP Text-to-Image Synthesis Based on Recurrent Affine Transformations
School of Artificial Intelligence, Guangxi Colleges and Universities Key Laboratory of AI Algorithm Engineering（人工智能学院、广西 Colleges and Universities AI 算法工程重点实验室）
Surgical resection is a common procedure in the treatment of pediatric posterior fossa tumors. However, surgical damage is often unavoidable and its association with postoperative complications is not well understood. A reliable localization and measure of cerebellar damage is fundamental to study the relationship between the damaged cerebellar regions and postoperative neurological outcomes. Existing cerebellum normalization methods are not reliable on postoperative scans, therefore current approaches to measure surgical damage rely on manual labelling. In this work, we develop a robust algor…
The Chinese University of Hong Kong（香港中文大学）；University of Science and Technology of China（中国科学技术大学）；SenseTime Research（商汤科技研究院）
Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the semantic label maps as inputs to the generator, or use them to modulate the activations in normalization layers via affine transformations. We argue that convolutional kernels in the generator should be aware of the distinct semantic labels at different locations when generating images. In order to better exploit the semantic layout for the image generator, we pro…
Rutgers University（罗格斯大学）；Samsung AI Center（三星人工智能中心）
In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual descriptions of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by a generative neural networks (GANs) aimed to generate realistic images conditioned on the text features. These works mainly focus on generating spatially compact and well-defined categories of objects, such as birds or flowers. In contrast, meal images are significantly more complex, con…
Shanghai Key Laboratory of Multidimensional Information Processing（上海市多维度信息处理重点实验室）；Key Laboratory of Advanced Theory and Application in Statistics & Data Science, East China Normal University（华东师范大学统计与数据科学前沿理论及应用重点实验室）
Novel view synthesis often needs the paired data from both the source and target views. This paper proposes a view translation model under cVAE-GAN framework without requiring the paired data. We design a conditional deformable module (CDM) which uses the view condition vectors as the filters to convolve the feature maps of the main branch in VAE. It generates several pairs of displacement maps to deform the features, like the 2D optical flows. The results are fed into the deformed feature based normalization module (DFNM), which scales and offsets the main branch feature, given its deformed o…
Bosch Center for AI（博世人工智能中心）；MPI for Informatics（马克斯·普朗克信息学研究所）；University of Tübingen（图宾根大学）
Prior work has extensively studied the latent space structure of GANs for unconditional image synthesis, enabling global editing of generated images by the unsupervised discovery of interpretable latent directions. However, the discovery of latent directions for conditional GANs for semantic image synthesis (SIS) has remained unexplored. In this work, we specifically focus on addressing this gap. We propose a novel optimization method for finding spatially disentangled class-specific directions in the latent space of pretrained SIS models. We show that the latent directions found by our method…
Advances in fluorescence microscopy enable acquisition of 3D image volumes with better image quality and deeper penetration into tissue. Segmentation is a required step to characterize and analyze biological structures in the images and recent 3D segmentation using deep learning has achieved promising results. One issue is that deep learning techniques require a large set of groundtruth data which is impractical to annotate manually for large 3D microscopy volumes. This paper describes a 3D deep learning nuclei segmentation method using synthetic 3D volumes for training. A set of synthetic vol…
These days deep learning is the fastest-growing area in the field of Machine Learning. Convolutional Neural Networks are currently the main tool used for image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this paper, we have focused on the most frequently mentioned problem in the field of machine learning, that is relatively poor generalization abilities. Partial remedies for this are regularization techniques e.g. dropout, batch normalization, weight dec…
Eindhoven University of Technology（埃因霍温理工大学）；Philips Research Laboratories（飞利浦研究院）；Philips Healthcare（飞利浦医疗）
We propose a hybrid controllable image generation method to synthesize anatomically meaningful 3D+t labeled Cardiac Magnetic Resonance (CMR) images. Our hybrid method takes the mechanistic 4D eXtended CArdiac Torso (XCAT) heart model as the anatomical ground truth and synthesizes CMR images via a data-driven Generative Adversarial Network (GAN). We employ the state-of-the-art SPatially Adaptive De-normalization (SPADE) technique for conditional image synthesis to preserve the semantic spatial information of ground truth anatomy. Using the parameterized motion model of the XCAT heart, we genera…
University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Microsoft Research（微软研究院）；DeepMind
Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the training images, which is dictated by the number of layers in the underlying neural network. Recent work has shown, however, that feeding spatial noise vectors into a fully convolutional neural network enables both generation of arbitrary resolution output images as well as training on arbitrary resolution training images. While this work has provided impressive empirical results, little theoretical interpretation was prov…
Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial layout (i.e., bounding boxes + class labels in an image lattice) and style (i.e., structural and appearance variations encoded by latent vectors), especially at high resolution. By reconfigurable, it means that a model can preserve the intrinsic one-to-many mapping from a given layout to multiple plausible images with different styles, and is adaptive with r…
Multiple Sclerosis (MS) is a chronic progressive neurological disease characterized by the development of lesions in the white matter of the brain. T2-fluid-attenuated inversion recovery (FLAIR) brain magnetic resonance imaging (MRI) provides superior visualization and characterization of MS lesions, relative to other MRI modalities. Longitudinal brain FLAIR MRI in MS, involving repetitively imaging a patient over time, provides helpful information for clinicians towards monitoring disease progression. Predicting future whole brain MRI examinations with variable time lag has only been attempte…
Rutgers University（罗格斯大学）；Samsung AI Center, Cambridge, UK（三星人工智能中心（剑桥））
In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual list of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by generative neural networks (GAN) aimed to generate realistic images conditioned on the text features. These works mainly focus on generating spatially compact and well-defined categories of objects, such as birds or flowers, but meal images are significantly more complex, consisting of multiple …
