An Optimized Architecture for Unpaired Image-to-Image Translation
Medi-Caps Institute of Science and Technology（梅迪卡普斯科学技术学院）
Mohan Nikam
备注：
Accepted to be published in Springer Advances in Intelligent Systems and Computing (AISC) Series 11156. Accepted for presentation in Springer ICANI (International Conference on Advanced computing, Networking and Informatics)-2018
Unpaired Image-to-Image translation aims to convert the image from one domain (input domain A) to another domain (target domain B), without providing paired examples for the training. The state-of-the-art, Cycle-GAN demonstrated the power of Generative Adversarial Networks with Cycle-Consistency Loss. While its results are promising, there is scope for optimization in the training process. This paper introduces a new neural network architecture, which only learns the translation from domain A to B and eliminates the need for reverse mapping (B to A), by introducing a new Deviation-loss term. Furthermore, few other improvements to the Cycle-GAN are found and utilized in this new architecture, contributing to significantly lesser training duration.
Unpaired image-to-image translation is a class of vision problems whose goal is to find the mapping between different image domains using unpaired training data. Cycle-consistency loss is a widely used constraint for such problems. However, due to the strict pixel-level constraint, it cannot perform geometric changes, remove large objects, or ignore irrelevant texture. In this paper, we propose a novel adversarial-consistency loss for image-to-image translation. This loss does not require the translated image to be translated back to be a specific source image but can encourage the translated …
Recently unpaired multi-domain image-to-image translation has attracted great interests and obtained remarkable progress, where a label vector is utilized to indicate multi-domain information. In this paper, we propose SAT (Show, Attend and Translate), an unified and explainable generative adversarial network equipped with visual attention that can perform unpaired image-to-image translation for multiple domains. By introducing an action vector, we treat the original translation tasks as problems of arithmetic addition and subtraction. Visual attention is applied to guarantee that only the reg…
Beijing University of Posts and Telecommunications（北京邮电大学）；Kuaishou Technology（快手科技）
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data. By utilizing CNN in extracting local semantics, various techniques have been developed to improve the translation performance. However, CNN-based generators lack the ability to capture long-range dependency to well exploit global semantics. Recently, Vision Transformers have been widely investigated for recognition tasks. Though appealing, it is inappropriate to simply transfer a recognition-based vision transformer to image-to-image translation due to the generati…
Tampere University of Technology（坦佩雷理工大学）；Aalto University of Technology（阿尔托理工大学）
Image-to-image translation is a general name for a task where an image from one domain is converted to a corresponding image in another domain, given sufficient training data. Traditionally different approaches have been proposed depending on whether aligned image pairs or two sets of (unaligned) examples from both domains are available for training. While paired training samples might be difficult to obtain, the unpaired setup leads to a highly under-constrained problem and inferior results. In this paper, we propose a new general purpose image-to-image translation model that is able to utili…
Generative Adversarial Networks (GANs) have been widely used for the image-to-image translation task. While these models rely heavily on the labeled image pairs, recently some GAN variants have been proposed to tackle the unpaired image translation task. These models exploited supervision at the domain level with a reconstruction process for unpaired image translation. On the other hand, parallel works have shown that leveraging perceptual loss functions based on high level deep features could enhance the generated image quality. Nevertheless, as these GAN-based models either depended on the p…
Many applications of unpaired image-to-image translation require the input contents to be preserved semantically during translations. Unaware of the inherently unmatched semantics distributions between source and target domains, existing distribution matching methods (i.e., GAN-based) can give undesired solutions. In particular, although producing visually reasonable outputs, the learned models usually flip the semantics of the inputs. To tackle this without using extra supervision, we propose to enforce the translated outputs to be semantically invariant w.r.t. small perceptual variations of …
University of Science and Technology of China (USTC)（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；Microsoft Research Asia（微软亚洲研究院）
Contrastive learning shows great potential in unpaired image-to-image translation, but sometimes the translated results are in poor quality and the contents are not preserved consistently. In this paper, we uncover that the negative examples play a critical role in the performance of contrastive learning for image translation. The negative examples in previous methods are randomly sampled from the patches of different positions in the source image, which are not effective to push the positive examples close to the query examples. To address this issue, we present instance-wise hard Negative Ex…
Meta Reality Labs（元宇宙现实实验室）；University of California, Berkeley（加州大学伯克利分校）
Image-to-image translation has played an important role in enabling synthetic data for computer vision. However, if the source and target domains have a large semantic mismatch, existing techniques often suffer from source content corruption aka semantic flipping. To address this problem, we propose a new paradigm for image-to-image translation using Vector Symbolic Architectures (VSA), a theoretical framework which defines algebraic operations in a high-dimensional vector (hypervector) space. We introduce VSA-based constraints on adversarial learning for source-to-target translations by learn…
KU Leuven（鲁汶大学）；University of Antwerp（安特卫普大学）；imec-IDLab
We address the problem of unpaired geometric image-to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object as depicted in different domains while preserving its appearance characteristics. Our model is trained in an unpaired fashion, i.e. without the need of paired images during training. It performs all steps of the shape transfer within a single model and without additional post-processing stages. Extensive experiments on the VITON, CMU-Multi-PIE and our own FashionStyle datasets show the effectiveness of the method.…
NCT/UCC Dresden（德累斯顿国家肿瘤疾病中心/大学癌症中心）；CeTI, TU Dresden（德累斯顿工业大学触觉互联网卓越中心）；University Hospital Dresden（德累斯顿大学医院）
Research in unpaired video translation has mainly focused on short-term temporal consistency by conditioning on neighboring frames. However for transfer from simulated to photorealistic sequences, available information on the underlying geometry offers potential for achieving global consistency across views. We propose a novel approach which combines unpaired image translation with neural rendering to transfer simulated to photorealistic surgical abdominal scenes. By introducing global learnable textures and a lighting-invariant view-consistency loss, our method produces consistent translation…
Robotics Institute（机器人研究所）；Carnegie Mellon University（卡内基梅隆大学）；School of Architecture（建筑学院）
While attention-based transformer networks achieve unparalleled success in nearly all language tasks, the large number of tokens (pixels) found in images coupled with the quadratic activation memory usage makes them prohibitive for problems in computer vision. As such, while language-to-language translation has been revolutionized by the transformer model, convolutional networks remain the de facto solution for image-to-image translation. The recently proposed MLP-Mixer architecture alleviates some of the computational issues associated with attention-based networks while still retaining the l…
Recently, image-to-image translation has been made much progress owing to the success of conditional Generative Adversarial Networks (cGANs). And some unpaired methods based on cycle consistency loss such as DualGAN, CycleGAN and DiscoGAN are really popular. However, it's still very challenging for translation tasks with the requirement of high-level visual information conversion, such as photo-to-caricature translation that requires satire, exaggeration, lifelikeness and artistry. We present an approach for learning to translate faces in the wild from the source photo domain to the target car…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；University of Rochester（罗切斯特大学）
Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs). However, existing approaches are mostly designed in an unsupervised manner while little attention has been paid to domain information within unpaired data. In this paper, we treat domain information as explicit supervision and design an unpaired image-to-image translation framework, Domain-supervised GAN (DosGAN), which takes the first step towards the exploration of explicit domain supervision. In contrast to representing domain characteristics using different generators or domain codes…
Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications
NCT/UCC Dresden（德累斯顿国家肿瘤疾病中心/德累斯顿肿瘤中心）；SECAI, TU Dresden（德累斯顿工业大学SECAI中心）；Faculty of medicine & University Hospital TU Dresden（德累斯顿工业大学医学院及大学医院）；CeTI, TU Dresden（德累斯顿工业大学CeTI中心）
Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN provide a general solution for any two domains through modeling injective mappings with a symmetric structure. While in situations where two domains are asymmetric in complexity, i.e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity. To address these issues, we propose Asymmetric GAN (AsymGAN) to adapt the asy…
The original publication Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks served as the inspiration for this implementation project. Researchers developed a novel method for doing image-to-image translations using an unpaired dataset in the original study. Despite the fact that the pix2pix models findings are good, the matched dataset is frequently not available. In the absence of paired data, cycleGAN can therefore get over this issue by converting images to images. In order to lessen the difference between the images, they implemented cycle consistency loss.I e…
Photorealistic image generation from simulated label maps are necessitated in several contexts, such as for medical training in virtual reality. With conventional deep learning methods, this task requires images that are paired with semantic annotations, which typically are unavailable. We introduce a contrastive learning framework for generating photorealistic images from simulated label maps, by learning from unpaired sets of both. Due to potentially large scene differences between real images and label maps, existing unpaired image translation methods lead to artifacts of scene modification…
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…
Faculty of Electrical Engineering and Computing, University of Zagreb（萨格勒布大学电气工程与计算学院）
Image-to-image translation models transfer images from input domain to output domain in an endeavor to retain the original content of the image. Contrastive Unpaired Translation is one of the existing methods for solving such problems. Significant advantage of this method, compared to competitors, is the ability to train and perform well in cases where both input and output domains are only a single image. Another key thing that differentiates this method from its predecessors is the usage of image patches rather than the whole images. It also turns out that sampling negatives (patches require…
Xiamen University（厦门大学）；Xi’an Jiaotong University（西安交通大学）；University of Chinese Academy of Sciences（中国科学院大学）
Unpaired Image-to-Image Translation (UIT) focuses on translating images among different domains by using unpaired data, which has received increasing research focus due to its practical usage. However, existing UIT schemes defect in the need of supervised training, as well as the lack of encoding domain information. In this paper, we propose an Attribute Guided UIT model termed AGUIT to tackle these two challenges. AGUIT considers multi-modal and multi-domain tasks of UIT jointly with a novel semi-supervised setting, which also merits in representation disentanglement and fine control of outpu…
Google Cloud AI（谷歌云人工智能）；Chinese Academy of Sciences（中国科学院）
The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations. In this paper, we take a manifold view of the problem by introducing a smoothness term over the sample graph to attain harmonic functions to enforce consistent mappings during the translation. We develop HarmonicGAN to learn bi-directional translations between the source and the target domains. With the …
Manga is a world popular comic form originated in Japan, which typically employs black-and-white stroke lines and geometric exaggeration to describe humans' appearances, poses, and actions. In this paper, we propose MangaGAN, the first method based on Generative Adversarial Network (GAN) for unpaired photo-to-manga translation. Inspired by how experienced manga artists draw manga, MangaGAN generates the geometric features of manga face by a designed GAN model and delicately translates each facial region into the manga domain by a tailored multi-GANs architecture. For training MangaGAN, we cons…
The University of Tokyo（东京大学）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所）；Tokyo Institute of Technology（东京工业大学）
Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial networks (GANs). However, due to the lack of explicit supervision, unpaired I2I models often fail to generate realistic images, especially in challenging datasets with different backgrounds and poses. Hence, stabilization is indispensable for GANs and applications of I2I translation. Herein, we propose Augmented Cyclic Consistency Regularization (ACCR), a novel regularization method for unpaired I2I translation. Our ma…
We propose a novel solution for unpaired image-to-image (I2I) translation. To translate complex images with a wide range of objects to a different domain, recent approaches often use the object annotations to perform per-class source-to-target style mapping. However, there remains a point for us to exploit in the I2I. An object in each class consists of multiple components, and all the sub-object components have different characteristics. For example, a car in CAR class consists of a car body, tires, windows and head and tail lamps, etc., and they should be handled separately for realistic I2I…
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…
We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models (UNIT-DDPM), trains a generative model to infer the joint distribution of images over both domains as a Markov chain by minimising a denoising score matching objective conditioned on the other domain. In particular, we update both domain translation models simultaneously, and we generate target domain images by a denoising Markov Chain Monte Carlo approach tha…
Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Soochow University（苏州大学）
There has been remarkable recent work in unpaired image-to-image translation. However, they're restricted to translation on single pairs of distributions, with some exceptions. In this study, we extend one of these works to a scalable multidistribution translation mechanism. Our translation models not only converts from one distribution to another but can be stacked to create composite translation functions. We show that this composite property makes it possible to generate images with characteristics not seen in the training set. We also propose a decoupled training mechanism to train multipl…
Harbin Institute of Technology（哈尔滨工业大学）；University of Trento（特伦托大学）；ETH Zurich（苏黎世联邦理工学院）；University of Oregon（俄勒冈大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Picsart AI Research (PAIR)（Picsart人工智能研究）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
The goal of unpaired image-to-image translation is to produce an output image reflecting the target domain's style while keeping unrelated contents of the input source image unchanged. However, due to the lack of attention to the content change in existing methods, the semantic information from source images suffers from degradation during translation. In the paper, to address this issue, we introduce a novel approach, Global and Local Alignment Networks (GLA-Net). The global alignment network aims to transfer the input image from the source domain to the target domain. To effectively do so, w…
In image-to-image translation the goal is to learn a mapping from one image domain to another. In the case of supervised approaches the mapping is learned from paired samples. However, collecting large sets of image pairs is often either prohibitively expensive or not possible. As a result, in recent years more attention has been given to techniques that learn the mapping from unpaired sets. In our work, we show that injecting implicit pairs into unpaired sets strengthens the mapping between the two domains, improves the compatibility of their distributions, and leads to performance boosting o…
Tel Aviv University（特拉维夫大学）；Hebrew University Jerusalem（耶路撒冷希伯来大学）
Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing between the images. This was made possible by introducing clever regularizers to overcome the under-constrained nature of the unpaired translation problem. In this work, we introduce a novel architecture for unpaired image translation, and explore several new regular…
SurgicaL-CD: Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Models
NCT/UCC Dresden（德累斯顿癌症中心/癌症联盟）；DKFZ Heidelberg（海德堡德国癌症研究中心）；Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology（德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯医学院及大学医院）；HZDR Dresden（德累斯顿亥姆霍兹中心）；The Centre for Tactile Internet with Human-in-the-Loop (CeTI), TUD Dresden University of Technology（德累斯顿工业大学人机交互触觉互联网中心）
Domain-Scalable Unpaired Image Translation via Latent Space Anchoring
John A. Paulson School of Engineering and Applied Sciences, Harvard University（哈佛大学约翰·A·保尔森工程与应用科学学院）；Amazon Alexa Science（亚马逊Alexa科学部）；Computer Science Department, Boston College（波士顿学院计算机科学系）
Beijing Institute of Technology（北京理工大学）；Yantai IRay Technologies Lt. Co.（烟台艾睿光电科技有限公司）
Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios. Thus, infrared cameras are often leveraged to help enhance the visual effects via detecting infrared radiation in the surrounding environment, but the infrared videos are undesirable due to the lack of detailed semantic information. In such a case, an effective video-to-video translation method from the infrared domain to the visible light counterpart is strongly needed by overcoming the intrinsic huge gap between infrared and visible fields. To address this challenging problem, we …
IBENS, ENS（巴黎高等师范学院生物研究所）；Université de Paris Cité（巴黎西岱大学）；Université de Paris（巴黎大学）
Unpaired image-to-image translation methods aim at learning a mapping of images from a source domain to a target domain. Recently, these methods proved to be very useful in biological applications to display subtle phenotypic cell variations otherwise invisible to the human eye. However, current models require a large number of images to be trained, while mostmicroscopy experiments remain limited in the number of images they can produce. In this work, we present an improved CycleGAN architecture that employs self-supervised discriminators to alleviate the need for numerous images. We demonstra…
VI-Diff: Unpaired Visible-Infrared Translation Diffusion Model for Single Modality Labeled Visible-Infrared Person Re-identification
University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；The Center for Research on Intelligent Perception and Computing (CRIPAC)（智能感知与计算研究中心）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
UC Berkeley（加州大学伯克利分校）；Berkeley AI Research (BAIR) laboratory（伯克利人工智能研究实验室）
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain $X$ to a target domain $Y$ in the absence of paired examples. Our goal is to learn a mapping $G: X \rightarrow Y$ such that the distribution of images from $G(X)$ is indistinguishable from the distribution $Y$ using an adversarial loss. Because this mappi…
College of Medicine, Seoul National University（首尔大学医学院）；Department of Radiology, Armed Forces Yangju Hospital（杨州国军医院放射科）
The purpose of this study is to apply and evaluate out-of-the-box deep learning frameworks for the crossMoDA challenge. We use the CUT model, a model for unpaired image-to-image translation based on patchwise contrastive learning and adversarial learning, for domain adaptation from contrast-enhanced T1 MR to high-resolution T2 MR. As data augmentation, we generate additional images with vestibular schwannomas with lower signal intensity. For the segmentation task, we use the nnU-Net framework. Our final submission achieved mean Dice scores of 0.8299 in the validation phase and 0.8253 in the te…
Image-to-image translation aims to preserve source contents while translating to discriminative target styles between two visual domains. Most works apply adversarial learning in the ambient image space, which could be computationally expensive and challenging to train. In this paper, we propose to deploy an energy-based model (EBM) in the latent space of a pretrained autoencoder for this task. The pretrained autoencoder serves as both a latent code extractor and an image reconstruction worker. Our model, LETIT, is based on the assumption that two domains share the same latent space, where lat…
University of California, Berkeley（加州大学伯克利分校）；Adobe Research（Adobe 研究院）
In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the two, using a framework based on contrastive learning. The method encourages two elements (corresponding patches) to map to a similar point in a learned feature space, relative to other elements (other patches) in the dataset, referred to as negatives. We explore several critical design choices for making contrastive learning effective in the image synthesis…
Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via generative-adversarial networks (GAN) coupled with the cycle-consistency constraint, while more recent works promote one-to-many mapping to boost diversity of the translated images. Motivated by scientific simulation and one-to-one needs, this work revisits the classic CycleGAN framework and boosts its performance to outperform more contemporary models without relaxing the cycle-cons…
KTH Royal Institute of Technology（KTH皇家理工学院）；Univrses AB（Univrses公司）
Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageable diversity of real-words situations. The main issue with unpaired image-to-image translation is the ill-posed nature of the problem. In this work, we propose a novel method for constraining the output space of unpaired image-to-image translation. We make the assumption that the environment of the source domain is known (e.g. synthetically generated), and we propose to explicitly enforce preservation of the ground-tr…
Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to other images, using supervised learning. Learning such mappings from unlabelled data, or improving upon supervised models by exploiting unlabelled data, remains elusive. We argue that there are two important parts to learning without annotations: (i) matching the predictions to the input observations, and (ii) matching the predictions to known priors. We propose Adversarial Inverse Graphics networks (AIGNs): weakly supervised neural network models t…
