Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
The University of Hong Kong（香港大学）；Adobe Research（Adobe研究）
Shilong Zhang, He Zhang, Zhifei Zhang, Chongjian Ge, Shuchen Xue, Shaoteng Liu, Mengwei Ren, Soo Ye Kim, Yuqian Zhou, Qing Liu, Daniil Pakhomov, Kai Zhang, Zhe Lin, Ping Luo
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents. However, we empirically identify two fundamental obstacles in this paradigm: (1) the discriminative feature space lacks compact regularization, making diffusion models prone to off-manifold latents that lead to inaccurate object structures; and (2) the encoder's inherently weak pixel-level reconstruction hinders the generator from learning accurate fine-grained geometry and texture. In this paper, we propose a systematic framework to adapt understanding-oriented encoder features for generative tasks. We introduce a semantic-pixel reconstruction objective to regularize the latent space, enabling the compression of both semantic information and fine-grained details into a highly compact representation (96 channels with 16x16 spatial downsampling). This design ensures that the latent space remains semantically rich and achieves state-of-the-art image reconstruction, while remaining compact enough for accurate generation. Leveraging this representation, we design a unified Text-to-Image (T2I) and image editing model. Benchmarking against various feature spaces, we demonstrate that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both T2I and editing tasks, validating that representation encoders can be effectively adapted into robust generative components.
University of Chinese Academy of Sciences（中国科学院大学）；Center for Research on Intelligent Perception and Computing, NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心）
GAN inversion has been exploited in many face manipulation tasks, but 2D GANs often fail to generate multi-view 3D consistent images. The encoders designed for 2D GANs are not able to provide sufficient 3D information for the inversion and editing. Therefore, 3D-aware GAN inversion is proposed to increase the 3D editing capability of GANs. However, the 3D-aware GAN inversion remains under-explored. To tackle this problem, we propose a 3D-aware (3Da) encoder for GAN inversion and face editing based on the powerful StyleNeRF model. Our proposed 3Da encoder combines a parametric 3D face model wit…
Technion - Israel Institute of Technology（以色列理工学院）
Understating and controlling generative models' latent space is a complex task. In this paper, we propose a novel method for learning to control any desired attribute in a pre-trained GAN's latent space, for the purpose of editing synthesized and real-world data samples accordingly. We perform Sim2Real learning, relying on minimal samples to achieve an unlimited amount of continuous precise edits. We present an Autoencoder-based model that learns to encode the semantics of changes between images as a basis for editing new samples later on, achieving precise desired results - example shown in F…
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…
GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing
MT Lab, Meitu Inc.（美图公司MT实验室）；Department of Computer Science and Technology, BNRist, IDG/McGovern Institute for Brain Research, Tsinghua University（清华大学计算机科学与技术系）
Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the exis…
The Chinese University of Hong Kong（香港中文大学）；Xiaomi AI Lab（小米人工智能实验室）
Recent work has shown that a variety of semantics emerge in the latent space of Generative Adversarial Networks (GANs) when being trained to synthesize images. However, it is difficult to use these learned semantics for real image editing. A common practice of feeding a real image to a trained GAN generator is to invert it back to a latent code. However, existing inversion methods typically focus on reconstructing the target image by pixel values yet fail to land the inverted code in the semantic domain of the original latent space. As a result, the reconstructed image cannot well support sema…
LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）；InterDigital R&I（交互数字研发中心）
We propose a novel architecture for GAN inversion, which we call Feature-Style encoder. The style encoder is key for the manipulation of the obtained latent codes, while the feature encoder is crucial for optimal image reconstruction. Our model achieves accurate inversion of real images from the latent space of a pre-trained style-based GAN model, obtaining better perceptual quality and lower reconstruction error than existing methods. Thanks to its encoder structure, the model allows fast and accurate image editing. Additionally, we demonstrate that the proposed encoder is especially well-sui…
The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, due to an inherent trade-off between reconstruction and editability: latent space regions which can accurately represent real images typically suffer from degraded semantic control. Recent work proposes to mitigate this trade-off by fine-tuning the generator to add the target image to well-behaved, editable regions of the latent space. While promising, this fine-tuning scheme is impractical for prevalent use as it req…
HUG-VAS: A Hierarchical NURBS-Based Generative Model for Aortic Geometry Synthesis and Controllable Editing
Department of Aerospace and Mechanical Engineering, University of Notre Dame（notre dame 大学航空航天与机械工程系）；Sibley School of Mechanical and Aerospace Engineering, Cornell University（cornell 大学机械与航空航天工程学院）；Department of Applied and Computational Mathematics and Statistics, University of Notre Dame（notre dame 大学应用与计算数学与统计学系）
MagicFace: High-Fidelity Facial Expression Editing with Action-Unit Control
Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu（机器视觉与信号分析中心，信息科技与电气工程学院，奥卢大学）
NAVER AI Lab（NAVER人工智能实验室）；Seoul National University（首尔国立大学）；Yonsei University（延世大学）
Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder. We propose StyleMapGAN: the intermediate latent space has spatial dimensions, and a spatially variant modulation replaces AdaIN. It makes the embedding through an encoder more accurate than existing optimization-based methods while maintaining the properties…
MiVE: Multiscale Vision-language features for reference-guided video Editing
MT Lab, Meitu Inc., Beijing 100083, China（美图实验室，美图公司，北京100083，中国）；Department of Computer Science and Technology, BNRist, IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China（计算机科学与技术系，BNRist，IDG/麦戈文脑研究学院，清华大学，北京100084，中国）；Beijing University of Posts（北京邮电大学）
Towards Consistent and Controllable Image Synthesis for Face Editing
Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu（机器视觉与信号分析中心，信息科技与电气工程学院，奥卢大学）；Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Sciences and Medical Engineering, Southeast University（教育部儿童发展与学习科学重点实验室，生物科学与医学工程学院，东南大学）
Generative Adversarial Networks (GANs) have recently demonstrated to successfully approximate complex data distributions. A relevant extension of this model is conditional GANs (cGANs), where the introduction of external information allows to determine specific representations of the generated images. In this work, we evaluate encoders to inverse the mapping of a cGAN, i.e., mapping a real image into a latent space and a conditional representation. This allows, for example, to reconstruct and modify real images of faces conditioning on arbitrary attributes. Additionally, we evaluate the design…
North China Electric Power University（华北电力大学）；Liaoning Shihua University（辽宁石油化工大学）；New Jersey Institute of Technology（新泽西理工学院）；Shandong University of Science and Technology（山东科技大学）
Facial attribute editing has mainly two objectives: 1) translating image from a source domain to a target one, and 2) only changing the facial regions related to a target attribute and preserving the attribute-excluding details. In this work, we propose a Multi-attention U-Net-based Generative Adversarial Network (MU-GAN). First, we replace a classic convolutional encoder-decoder with a symmetric U-Net-like structure in a generator, and then apply an additive attention mechanism to build attention-based U-Net connections for adaptively transferring encoder representations to complement a decod…
Attribution editing has achieved remarkable progress in recent years owing to the encoder-decoder structure and generative adversarial network (GAN). However, it remains challenging in generating high-quality images with accurate attribute transformation. Attacking these problems, the work proposes a novel selective attribute editing model based on classification adversarial network (referred to as ClsGAN) that shows good balance between attribute transfer accuracy and photo-realistic images. Considering that the editing images are prone to be affected by original attribute due to skip-connect…
Tsinghua University（清华大学）；Tencent AI Lab（腾讯人工智能实验室）；ByteDance Inc.（字节跳动公司）
Existing 3D-aware facial generation methods face a dilemma in quality versus editability: they either generate editable results in low resolution or high-quality ones with no editing flexibility. In this work, we propose a new approach that brings the best of both worlds together. Our system consists of three major components: (1) a 3D-semantics-aware generative model that produces view-consistent, disentangled face images and semantic masks; (2) a hybrid GAN inversion approach that initialize the latent codes from the semantic and texture encoder, and further optimized them for faithful recon…
The high-quality images yielded by generative adversarial networks (GANs) have motivated investigations into their application for image editing. However, GANs are often limited in the control they provide for performing specific edits. One of the principal challenges is the entangled latent space of GANs, which is not directly suitable for performing independent and detailed edits. Recent editing methods allow for either controlled style edits or controlled semantic edits. In addition, methods that use semantic masks to edit images have difficulty preserving the identity and are unable to per…
EleutherAI；Booz Allen Hamilton（博思艾伦汉密尔顿）；AIDock；Georgia Institute of Technology（佐治亚理工学院）
Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel methodology for both tasks which is capable of producing images of high visual quality from text prompts of significant semantic complexity without any training by using a multimodal encoder to guide image generations. We demonstrate on a variety of tasks how using CLIP [37] to guide VQGAN [11] produces higher visual quality outputs than prior, less flexible approaches like DALL-E [38], GLIDE [33] and Open-Edit [24], despi…
University of Maryland, College Park（马里兰大学帕克分校）；PARC, Palo Alto（帕洛阿尔托帕罗奥多研究中心）
Facial expression editing is a challenging task as it needs a high-level semantic understanding of the input face image. In conventional methods, either paired training data is required or the synthetic face resolution is low. Moreover, only the categories of facial expression can be changed. To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity. An expression controller module is specially designed to learn an expressive and compact expression code in addition to the …
Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details. Recently, generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results. Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of the given face conditioned on the desired attributes. Some existing methods attempt to establish an attribute-independent latent representation for further at…
Recently there has been an enormous interest in generative models for images in deep learning. In pursuit of this, Generative Adversarial Networks (GAN) and Variational Auto-Encoder (VAE) have surfaced as two most prominent and popular models. While VAEs tend to produce excellent reconstructions but blurry samples, GANs generate sharp but slightly distorted images. In this paper we propose a new model called Variational InfoGAN (ViGAN). Our aim is two fold: (i) To generated new images conditioned on visual descriptions, and (ii) modify the image, by fixing the latent representation of image an…
Generating random photo-realistic images has experienced tremendous growth during the past few years due to the advances of the deep convolutional neural networks and generative models. Among different domains, face photos have received a great deal of attention and a large number of face generation and manipulation models have been proposed. Semantic facial attribute editing is the process of varying the values of one or more attributes of a face image while the other attributes of the image are not affected. The requested modifications are provided as an attribute vector or in the form of dr…
University of Rochester（罗切斯特大学）；Adobe Research（Adobe研究院）
Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified model for open-domain image editing focusing on color and tone adjustment of open-domain images while keeping their original content and structure. Our model learns a unified editing space that is more semantic, intuitive, and easy to manipulate than the operation space (e.g., contrast, brightness, color curve) used in many existing photo editing softwares.…
In this paper, we use a tensor model based on the Higher-Order Singular Value Decomposition (HOSVD) to discover semantic directions in Generative Adversarial Networks. This is achieved by first embedding a structured facial expression database into the latent space using the e4e encoder. Specifically, we discover directions in latent space corresponding to the six prototypical emotions: anger, disgust, fear, happiness, sadness, and surprise, as well as a direction for yaw rotation. These latent space directions are employed to change the expression or yaw rotation of real face images. We compa…
Huya Inc（虎牙公司）；City University of Hong Kong（香港城市大学）；Hunan University（湖南大学）；Tencent AI Lab（腾讯AI实验室）；Tencent Data Platform（腾讯数据平台）
User-intended visual content fills the hole regions of an input image in the image editing scenario. The coarse low-level inputs, which typically consist of sparse sketch lines and color dots, convey user intentions for content creation (\ie, free-form editing). While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content. In this paper, we propose DeFLOCNet which relies on a deep encoder-decoder CNN to retain the guidance of these cont…
A Diffusion Model for Simulation Ready Coronary Anatomy with Morpho-skeletal Control
Institute of Medical Engineering, MIT（麻省理工学院医学工程研究所）；Brigham and Women's Hospital, Harvard（哈佛大学布莱尔妇女医院）；HeartFlow（HeartFlow公司）；Showa University（昭和大学）；OLV Aalst
Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Adobe Research（Adobe研究院）；Tel-Aviv University（特拉维夫大学）
StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 architecture, compare it to its predecessor, and investigate its unique advantages, as well as drawbacks. In particular, we demonstrate that while StyleGAN3 can be trained on unaligned data, one can still use aligned data for training, without hindering the ability to generate unaligned imagery. Next, our analysis of the disentanglement of the different latent spaces of StyleGAN3 …
SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
University of Macau（澳门大学）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；Tencent AI Lab（腾讯人工智能实验室）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Tsinghua University（清华大学）
