Diffusion models have emerged as the leading approach for style transfer, yet they struggle with photo-realistic transfers, often producing painting-like results or missing detailed stylistic elements. Current methods inadequately address unwanted influence from original content styles and style reference content features. We introduce SCAdapter, a novel technique leveraging CLIP image space to effectively separate and integrate content and style features. Our key innovation systematically extracts pure content from content images and style elements from style references, ensuring authentic transfers. This approach is enhanced through three components: Controllable Style Adaptive Instance Normalization (CSAdaIN) for precise multi-style blending, KVS Injection for targeted style integration, and a style transfer consistency objective maintaining process coherence. Comprehensive experiments demonstrate SCAdapter significantly outperforms state-of-the-art methods in both conventional and diffusion-based baselines. By eliminating DDIM inversion and inference-stage optimization, our method achieves at least $2\times$ faster inference than other diffusion-based approaches, making it both more effective and efficient for practical applications.
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…
University of Edinburgh（爱丁堡大学）；IMT School for Advanced Studies Lucca（卢卡高等研究院）；Canon Medical Research Europe Ltd.（佳能医疗欧洲研究有限公司）；The Alan Turing Institute（艾伦·图灵研究所）
A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially equivariant tasks (e.g. image-to-image translation). To achieve this, they employ different model design, learning objective, and data biases. While considerable effort has been made to measure disentanglement in vector representations, and assess its impact on task performance, such analysis for (spatial) content - style disentanglement is lacking. In this paper, we conduct an e…
In this work, we propose and validate a framework to leverage language-image pretraining representations for training-free zero-shot sketch-to-image synthesis. We show that disentangled content and style representations can be utilized to guide image generators to employ them as sketch-to-image generators without (re-)training any parameters. Our approach for disentangling style and content entails a simple method consisting of elementary arithmetic assuming compositionality of information in representations of input sketches. Our results demonstrate that this approach is competitive with stat…
Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in an unsupervised fashion and capture the most significant factors of the data variations. However, these approaches ignore the principle of content and style disentanglement in image generation, which means their learned latent code may alter the content and style of the generated images at the same time. This paper describes the Style and Content Disentangl…
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks. However, due to the unexplored independence and exclusiveness in the labels, existing endeavors are defeated by involving uncontrolled manipulations to the translation results. In this paper, we propose Hierarchical Style Disentanglement (HiSD) to address this issue. Specifically, we organize the labels into a hierarchical tree structure, in which independent tags, exclusive attributes, a…
We propose a way of learning disentangled content-style representation of image, allowing us to extrapolate images to any style as well as interpolate between any pair of styles. By augmenting data set in a supervised setting and imposing triplet loss, we ensure the separation of information encoded by content and style representation. We also make use of cycle-consistency loss to guarantee that images could be reconstructed faithfully by their representation.
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…
Unsupervised image-to-image translation methods have achieved tremendous success in recent years. However, it can be easily observed that their models contain significant entanglement which often hurts the translation performance. In this work, we propose a principled approach for improving style-content disentanglement in image-to-image translation. By considering the information flow into each of the representations, we introduce an additional loss term which serves as a content-bottleneck. We show that the results of our method are significantly more disentangled than those produced by curr…
Rice University（莱斯大学）；Nvidia（英伟达）；University of Toronto（多伦多大学）；California Institute of Technology（加州理工学院）
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on learning disentangled representations, and non-identifiability due to the unsupervised setting. To alleviate these limitations, we design new architectures and loss functions based on StyleGAN (Karras et al., 2019), for semi-supervised high-resolution disentanglement learning. We create two complex high-resolution synthetic datasets for systematic testing. We i…
Xi’an Jiaotong University（西安交通大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tsinghua University（清华大学）
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i.e.style feature, and the feature representing the invariant semantic content, i.e. content feature. Previous methods separate content feature apart by utilizing it to classify haze image during the training process. However, in this paper we recognize the incompleteness of the content-style disentanglement in such technical routine. The flawed style feature entangled with content information inevitably leads the ill-rendering of the haze im…
Free-Lunch Color-Texture Disentanglement for Stylized Image Generation
Harbin Institute of Technology, China（哈尔滨工业大学）；VCIP, CS, Nankai University, China（南开大学）；Computer Vision Center, Spain（西班牙计算机视觉中心）；Universitat Autònoma de Barcelona, Spain（巴塞罗那自治大学）；Program of Computer Science, City University of Hong Kong (Dongguan), China（香港城市大学（东莞）计算机科学系）；City University of Hong Kong, HK SAR, China（香港城市大学）
Privacy of machine learning models is one of the remaining challenges that hinder the broad adoption of Artificial Intelligent (AI). This paper considers this problem in the context of image datasets containing faces. Anonymization of such datasets is becoming increasingly important due to their central role in the training of autonomous cars, for example, and the vast amount of data generated by surveillance systems. While most prior work de-identifies facial images by modifying identity features in pixel space, we instead project the image onto the latent space of a Generative Adversarial Ne…
UC, Santa Barbara（加州大学圣巴巴拉分校）；Adobe Research（奥多比研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Generative models have been widely studied in computer vision. Recently, diffusion models have drawn substantial attention due to the high quality of their generated images. A key desired property of image generative models is the ability to disentangle different attributes, which should enable modification towards a style without changing the semantic content, and the modification parameters should generalize to different images. Previous studies have found that generative adversarial networks (GANs) are inherently endowed with such disentanglement capability, so they can perform disentangled…
We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation learning concepts to make the disentangled latent representations easily interpreted as well. We start by coupling StyleGAN with a stabilized 3D deformable facial reconstruction method to decompose single-view GAN generations into multiple semantics. Latent representations are then extracted to capture interpretable facial semantics. In this work, we make it possible to get rid of labels for disentangling meaningful f…
King Abdullah University for Science and Technology (KAUST)（阿卜杜拉国王科技大学）
We explore different design choices for injecting noise into generative adversarial networks (GANs) with the goal of disentangling the latent space. Instead of traditional approaches, we propose feeding multiple noise codes through separate fully-connected layers respectively. The aim is restricting the influence of each noise code to specific parts of the generated image. We show that disentanglement in the first layer of the generator network leads to disentanglement in the generated image. Through a grid-based structure, we achieve several aspects of disentanglement without complicating the…
Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to an input real image. This editing property emerges from the disentangled nature of the latent space. In this paper, we identify that the facial attribute disentanglement is not optimal, thus facial editing relying on linear attribute separation is flawed. We thus propose to improve semantic disentanglement with supervision. Our method consists in learning a proxy latent representation using normalizing flows, and we show that this lead…
Tencent AI Lab（腾讯人工智能实验室）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；South China University of Technology（华南理工大学）
We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective of fine-grained face editing, \textit{i.e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components. Following the E4S principle, our framework enables both global and local swapping of facial features, as well as controlling the amount of partial swapping specified by the user. Furthermore, the E4S paradigm is inherently ca…
Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation
State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室）；School of Artificial Intelligence, Nanjing University, China（人工智能学院）；Department of Computer Science and Technology, Nanjing University, China（计算机科学与技术系）；School of Electronic Science and Engineering, Nanjing University, China（电子科学与工程学院）
MLSD-GAN -- Generating Strong High Quality Face Morphing Attacks using Latent Semantic Disentanglement
Advanced Technology Development Centre, IIT Kharagpur（印度理工学院克勒格布尔分校先进技术发展中心）；Norwegian University of Science and Technology (NTNU)（挪威科技大学）；Department of Computer Science and Engineering, IIT Kharagpur（印度理工学院克勒格布尔分校计算机科学与工程系）
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）；Massachusetts Institute of Technology（麻省理工学院）；Friedrich-Alexander-University Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）；Michigan State University（密歇根州立大学）
Recent advances in generative adversarial networks (GANs) have led to remarkable achievements in face image synthesis. While methods that use style-based GANs can generate strikingly photorealistic face images, it is often difficult to control the characteristics of the generated faces in a meaningful and disentangled way. Prior approaches aim to achieve such semantic control and disentanglement within the latent space of a previously trained GAN. In contrast, we propose a framework that a priori models physical attributes of the face such as 3D shape, albedo, pose, and lighting explicitly, th…
Tsinghua University（清华大学）；University College London（伦敦大学学院）
Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be formulated as image-to-image translation problems. However, three main challenges remain in image-to-image translation: 1) the lack of large amounts of aligned training pairs for different tasks; 2) the ambiguity of multiple possible outputs from a single input image; and 3) the lack of simultaneous training of multiple datasets from different domains within a s…
Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to enforce an explicit disentanglement between content and style latent representations, making the content and style of generated samples consistent with their corresponding content and style references. The model is also constrained by a content alignment loss to ensure the foreground editing will not interfere background contents. As a result, given interested re…
University of Southern California（南加州大学）；Pinscreen；USC Institute for Creative Technologies（南加州大学创意技术研究所）
Existing methods for AI-generated artworks still struggle with generating high-quality stylized content, where high-level semantics are preserved, or separating fine-grained styles from various artists. We propose a novel Generative Adversarial Disentanglement Network which can disentangle two complementary factors of variations when only one of them is labelled in general, and fully decompose complex anime illustrations into style and content in particular. Training such model is challenging, since given a style, various content data may exist but not the other way round. Our approach is divi…
The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation using StyleGAN2. First, we propose a novel approach to disentangle latent subspace semantics by exploiting existing face analysis models, e.g., face parsers and face landmark detectors. These models provide the flexibility to construct various criterions with very concrete and interpretable semantic meanings (e.g., change face shape or change skin color) to restrict latent sub…
AI-driven image generation has improved significantly in recent years. Generative adversarial networks (GANs), like StyleGAN, are able to generate high-quality realistic data and have artistic control over the output, as well. In this work, we present StyleT2F, a method of controlling the output of StyleGAN2 using text, in order to be able to generate a detailed human face from textual description. We utilize StyleGAN's latent space to manipulate different facial features and conditionally sample the required latent code, which embeds the facial features mentioned in the input text. Our method…
This paper introduces MakeupBag, a novel method for automatic makeup style transfer. Our proposed technique can transfer a new makeup style from a reference face image to another previously unseen facial photograph. We solve makeup disentanglement and facial makeup application as separable objectives, in contrast to other current deep methods that entangle the two tasks. MakeupBag presents a significant advantage for our approach as it allows customization and pixel specific modification of the extracted makeup style, which is not possible using current methods. Extensive experiments, both qua…
Visually-Guided Controllable Medical Image Generation via Fine-Grained Semantic Disentanglement
Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程系，中国沈阳）；Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China（教育部医学图像智能计算重点实验室，东北大学，中国沈阳）；National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China（工业智能与系统优化国家级前沿科学中心，中国沈阳）；AiShiWeiLai AI Research, China（艾世维来人工智能研究，中国）；Amii, University of Alberta, Edmonton, Alberta, Canada（阿尔伯塔大学艾米人工智能研究所，加拿大埃德蒙顿，阿尔伯塔）
StyleMorpheus: A Style-Based 3D-Aware Morphable Face Model
Department of Electrical and Computer Engineering, The University of British Columbia（电气与计算机工程系，不列颠哥伦比亚大学）；Huawei Technologies Canada（华为技术加拿大公司）；Department of Computer Science, Mathematics, Physics and Statistics, The University of British Columbia (Okanagan)（计算机科学、数学、物理与统计学系，不列颠哥伦比亚大学（OKanagan））
University of Electronic Science and Technology of China（电子科技大学）；Shanghai AI Lab（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；ShanghaiTech University（上海科技大学）；Sensetime Research（商汤科技研究院）；Sichuan University（四川大学）；Sichuan Cancer Hospital and Institute（四川省肿瘤医院（四川省肿瘤研究所））
Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to disentangle domain-specific and domain-invariant features is key for achieving Domain Generalization (DG). However, existing DG methods can hardly achieve effective disentanglement to get high generalizability. To deal with this problem, we propose an efficient Contrastive Domain Disentanglement and Style Augmentation (CDDSA) framework for generalizable medical image segmentation. First, a disentangle network is propo…
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；College of Computer Science, Nankai University（南开大学计算机学院）
EPFL（洛桑联邦理工学院）；Palo Alto Research Center（帕洛阿尔托研究中心）
While the quality of GAN image synthesis has improved tremendously in recent years, our ability to control and condition the output is still limited. Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image. This is accomplished by borrowing elements from a source image, also a GAN output, via a novel manipulation of style vectors. Our method requires neither supervision from an external model, nor involves complex spatial morphing operations. Instead, it relies on the emergent disentanglement of semantic objects that …
