Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to their high performance and flexibility in hardware choice. However, collecting ground truth data for supervised training of these algorithms is costly or outright impossible. This circumstance suggests a need for alternative learning approaches that do not require corresponding depth measurements. Indeed, self-supervised learning of depth estimation provides an increasingly popular alternative. It is based on the idea that observed frames can be synthesized from neighboring frames if accurate depth of the scene is known - or in this case, estimated. We show empirically that - contrary to common belief - improvements in image synthesis do not necessitate improvement in depth estimation. Rather, optimizing for image synthesis can result in diverging performance with respect to the main prediction objective - depth. We attribute this diverging phenomenon to aleatoric uncertainties, which originate from data. Based on our experiments on four datasets (spanning street, indoor, and medical) and five architectures (monocular and stereo), we conclude that this diverging phenomenon is independent of the dataset domain and not mitigated by commonly used regularization techniques. To underscore the importance of this finding, we include a survey of methods which use image synthesis, totaling 127 papers over the last six years. This observed divergence has not been previously reported or studied in depth, suggesting room for future improvement of self-supervised approaches which might be impacted the finding.
Heidelberg University（海德堡大学）；University of Bath（巴斯大学）；NVIDIA（英伟达）
We present SSOD, the first end-to-end analysis-by synthesis framework with controllable GANs for the task of self-supervised object detection. We use collections of real world images without bounding box annotations to learn to synthesize and detect objects. We leverage controllable GANs to synthesize images with pre-defined object properties and use them to train object detectors. We propose a tight end-to-end coupling of the synthesis and detection networks to optimally train our system. Finally, we also propose a method to optimally adapt SSOD to an intended target data without requiring la…
TReViS: Temporal Repetition Structure Aware Video Synthesis for Self-supervised Repetitive Action Counting
AIGO Unit, Istituto Italiano di Tecnologia（意大利技术研究院AIGO单元）；Department of Computer Science, University of Verona（维罗纳大学计算机科学系）；University of Genoa（热那亚大学）
Pohang University of Science and Technology（浦项科技大学）
Text-to-image synthesis aims to generate a photo-realistic image from a given natural language description. Previous works have made significant progress with Generative Adversarial Networks (GANs). Nonetheless, it is still hard to generate intact objects or clear textures (Fig 1). To address this issue, we propose Feature-Aware Generative Adversarial Network (FA-GAN) to synthesize a high-quality image by integrating two techniques: a self-supervised discriminator and a feature-aware loss. First, we design a self-supervised discriminator with an auxiliary decoder so that the discriminator can …
Stony Brook University（石溪大学）；Dougherty Valley High School（多尔蒂谷高中）；Oak Ridge National Laboratory（橡树岭国家实验室）；Stony Brook Hospital（石溪医院）
Hematoxylin and Eosin stained histopathology image analysis is essential for the diagnosis and study of complicated diseases such as cancer. Existing state-of-the-art approaches demand extensive amount of supervised training data from trained pathologists. In this work we synthesize in an unsupervised manner, large histopathology image datasets, suitable for supervised training tasks. We propose a unified pipeline that: a) generates a set of initial synthetic histopathology images with paired information about the nuclei such as segmentation masks; b) refines the initial synthetic images throu…
University of Amsterdam（阿姆斯特丹大学）；Shanghai Jiao Tong University（上海交通大学）
This paper strives to generate a synthetic computed tomography (CT) image from a magnetic resonance (MR) image. The synthetic CT image is valuable for radiotherapy planning when only an MR image is available. Recent approaches have made large strides in solving this challenging synthesis problem with convolutional neural networks that learn a mapping from MR inputs to CT outputs. In this paper, we find that all existing approaches share a common limitation: reconstruction breaks down in and around the high-frequency parts of CT images. To address this common limitation, we introduce frequency-…
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend on a huge amount of labeled data and cannot be applied in an unpaired setting. On the other hand, generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and feed them to traditional convolutional networks, which then learn correspondences in appearance instead of semantic content. In this …
Pseudo-normality synthesis, which computationally generates a pseudo-normal image from an abnormal one (e.g., with lesions), is critical in many perspectives, from lesion detection, data augmentation to clinical surgery suggestion. However, it is challenging to generate high-quality pseudo-normal images in the absence of the lesion information. Thus, expensive lesion segmentation data have been introduced to provide lesion information for the generative models and improve the quality of the synthetic images. In this paper, we aim to alleviate the need of a large amount of lesion segmentation d…
Inception Institute of Artificial Intelligence（起源人工智能研究院）；Indian Institute of Technology, Kanpur（印度理工学院坎普尔分校）
While medical image segmentation is an important task for computer aided diagnosis, the high expertise requirement for pixelwise manual annotations makes it a challenging and time consuming task. Since conventional data augmentations do not fully represent the underlying distribution of the training set, the trained models have varying performance when tested on images captured from different sources. Most prior work on image synthesis for data augmentation ignore the interleaved geometric relationship between different anatomical labels. We propose improvements over previous GAN-based medical…
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…
University of Science and Technology of China（中国科学技术大学）；Alibaba Group（阿里巴巴集团）；City University of Hong Kong（香港城市大学）
Recent efforts on scene text erasing have shown promising results. However, existing methods require rich yet costly label annotations to obtain robust models, which limits the use for practical applications. To this end, we study an unsupervised scenario by proposing a novel Self-supervised Text Erasing (STE) framework that jointly learns to synthesize training images with erasure ground-truth and accurately erase texts in the real world. We first design a style-aware image synthesis function to generate synthetic images with diverse styled texts based on two synthetic mechanisms. To bridge t…
Imagining a colored realistic image from an arbitrarily drawn sketch is one of the human capabilities that we eager machines to mimic. Unlike previous methods that either requires the sketch-image pairs or utilize low-quantity detected edges as sketches, we study the exemplar-based sketch-to-image (s2i) synthesis task in a self-supervised learning manner, eliminating the necessity of the paired sketch data. To this end, we first propose an unsupervised method to efficiently synthesize line-sketches for general RGB-only datasets. With the synthetic paired-data, we then present a self-supervised…
University of Nevada, Reno（内华达大学雷诺分校）；Houston Eye Associates（休斯顿眼科协会）
In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, and even death. In contrast, color fundus imaging is a non-invasive technique used for photographing the retina but does not have sufficient fidelity for capturing its vascular structure. The only non-invasive method for capturing retinal vasculature is optical coherence tomography-angiography (OCTA). However, OCTA equipment is quite expensive, and stable imaging is limited to s…
We propose a method for scene-level sketch-to-photo synthesis with text guidance. Although object-level sketch-to-photo synthesis has been widely studied, whole-scene synthesis is still challenging without reference photos that adequately reflect the target style. To this end, we leverage knowledge from recent large-scale pre-trained generative models, resulting in text-guided sketch-to-photo synthesis without the need for reference images. To train our model, we use self-supervised learning from a set of photographs. Specifically, we use a pre-trained edge detector that maps both color and sk…
A comprehensive understanding of vision and language and their interrelation are crucial to realize the underlying similarities and differences between these modalities and to learn more generalized, meaningful representations. In recent years, most of the works related to Text-to-Image synthesis and Image-to-Text generation, focused on supervised generative deep architectures to solve the problems, where very little interest was placed on learning the similarities between the embedding spaces across modalities. In this paper, we propose a novel self-supervised deep learning based approach tow…
Institut de Robòtica i Informàtica Industrial (CSIC-UPC)（工业机器人与信息技术研究所（西班牙国家研究委员会-加泰罗尼亚理工大学））
We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the image of the same person under the new pose, synthesizing novel views of the parts visible in the input image and hallucinating those that are not seen. This problem has recently been addressed in a supervised manner, i.e., during training the ground truth images under the new poses are given to the network. We go beyond these approaches by proposing a fully…
Fetal brain magnetic resonance imaging (MRI) offers exquisite images of the developing brain but is not suitable for second-trimester anomaly screening, for which ultrasound (US) is employed. Although expert sonographers are adept at reading US images, MR images which closely resemble anatomical images are much easier for non-experts to interpret. Thus in this paper we propose to generate MR-like images directly from clinical US images. In medical image analysis such a capability is potentially useful as well, for instance for automatic US-MRI registration and fusion. The proposed model is end…
Shenzhen University（深圳大学）；Shenzhen RayShape Medical Technology Co., Ltd（深圳瑞影医疗科技有限公司）；Huizhou Central People’s Hospital（惠州市中心人民医院）
Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical information. This is challenging for novices to learn because practicing with adequate videos from patients is clinically unpractical. In this paper, we propose a novel framework to synthesize high-fidelity US videos. Specifically, the synthesis videos are generated by animating source content images based on the motion of given driving videos. Our highlights are th…
University of Tsukuba（筑波大学）；Toyohashi University of Technology（丰桥技术科学大学）
Automatic generation of a high-quality video from a single image remains a challenging task despite the recent advances in deep generative models. This paper proposes a method that can create a high-resolution, long-term animation using convolutional neural networks (CNNs) from a single landscape image where we mainly focus on skies and waters. Our key observation is that the motion (e.g., moving clouds) and appearance (e.g., time-varying colors in the sky) in natural scenes have different time scales. We thus learn them separately and predict them with decoupled control while handling future …
L’Oréal Research and Innovation（欧莱雅研发与创新中心）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎综合理工学院电信巴黎理工高等通信学院LTCI实验室）
While existing makeup style transfer models perform an image synthesis whose results cannot be explicitly controlled, the ability to modify makeup color continuously is a desirable property for virtual try-on applications. We propose a new formulation for the makeup style transfer task, with the objective to learn a color controllable makeup style synthesis. We introduce CA-GAN, a generative model that learns to modify the color of specific objects (e.g. lips or eyes) in the image to an arbitrary target color while preserving background. Since color labels are rare and costly to acquire, our m…
University of Ljubljana（卢布尔雅那大学）；XLAB d.o.o.（XLAB公司）
Anomaly detection in visual data refers to the problem of differentiating abnormal appearances from normal cases. Supervised approaches have been successfully applied to different domains, but require an abundance of labeled data. Due to the nature of how anomalies occur and their underlying generating processes, it is hard to characterize and label them. Recent advances in deep generative-based models have sparked interest in applying such methods for unsupervised anomaly detection and have shown promising results in medical and industrial inspection domains. In this work we evaluate a crucia…
Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis
ShanghaiTech University（上海科技大学）；Nanjing University of Science and Technology（南京理工大学）；Nanjing University（南京大学）；National Institute of Healthcare Data Science at Nanjing University（南京大学医疗健康数据科学国家研究院）；Southeast University（东南大学）；Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能有限公司）；Shanghai Clinical Research and Trial Center（上海临床研究中心）
Korea Advanced Institute of Science and Technology（韩国科学技术院）；School of Electrical Engineering（电气工程学院）
Self-supervised depth estimators have recently shown results comparable to the supervised methods on the challenging single image depth estimation (SIDE) task, by exploiting the geometrical relations between target and reference views in the training data. However, previous methods usually learn forward or backward image synthesis, but not depth estimation, as they cannot effectively neglect occlusions between the target and the reference images. Previous works rely on rigid photometric assumptions or the SIDE network to infer depth and occlusions, resulting in limited performance. On the othe…
Medical image segmentation is routinely performed to isolate regions of interest, such as organs and lesions. Currently, deep learning is the state of the art for automatic segmentation, but is usually limited by the need for supervised training with large datasets that have been manually segmented by trained clinicians. The goal of semi-superised and unsupervised image segmentation is to greatly reduce, or even eliminate, the need for training data and therefore to minimze the burden on clinicians when training segmentation models. To this end we introduce a novel network architecture for cap…
University of Sheffield（谢菲尔德大学）；University of East Anglia（东英吉利大学）；University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Northumbria University（诺森比亚大学）
Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable. In this paper, we propose a new Zero-shot learning (ZSL) framework that can synthesise visual features for unseen classes without acquiring real images. Using the proposed Unseen Visual Data Synthesis (UVDS) algorithm, semantic attributes are effectively utilised as an intermediate clue to synthesise unseen visual features at the training stage. Hereafter, …
NYU（纽约大学）；NVidia（英伟达）；Technical University of Berlin（柏林工业大学）；Google（谷歌）
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations. Our method capitalizes on moving characters being equivariant with respect to their transformation across frames and the background being constant with respect to that same transformation. After training, we can manipulate image encodings in real time to create unseen combinations of the delineated components. As far as we know, we are the first method to perform unsupervised extraction and synthesis of interpretable background, c…
Peng Cheng Laboratory（鹏城实验室）；Dalian University of Technology（大连理工大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；University of California at Merced（加州大学默塞德分校）
While deep-learning based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training. To eliminate expensive and exhaustive annotation, we study self-supervised learning for visual tracking. In this work, we develop the Crop-Transform-Paste operation, which is able to synthesize sufficient training data by simulating various appearance variations during tracking, including appearance variations of objects and background interference. Since the target state is known in all synthesized data, existing deep trackers can be t…
The University of Hong Kong（香港大学）；Baidu Research（百度研究院）
Face sketch synthesis has made great progress in the past few years. Recent methods based on deep neural networks are able to generate high quality sketches from face photos. However, due to the lack of training data (photo-sketch pairs), none of such deep learning based methods can be applied successfully to face photos in the wild. In this paper, we propose a semi-supervised deep learning architecture which extends face sketch synthesis to handle face photos in the wild by exploiting additional face photos in training. Instead of supervising the network with ground truth sketches, we first p…
Australian National University and ACRV（澳大利亚国立大学与ACRV）；University of Technology Sydney（悉尼科技大学）
We address the problem of novel view synthesis (NVS) from a few sparse source view images. Conventional image-based rendering methods estimate scene geometry and synthesize novel views in two separate steps. However, erroneous geometry estimation will decrease NVS performance as view synthesis highly depends on the quality of estimated scene geometry. In this paper, we propose an end-to-end NVS framework to eliminate the error propagation issue. To be specific, we construct a volume under the target view and design a source-view visibility estimation (SVE) module to determine the visibility of…
Indian Institute of Science（印度科学学院）；Google Research（谷歌研究院）
Camera captured human pose is an outcome of several sources of variation. Performance of supervised 3D pose estimation approaches comes at the cost of dispensing with variations, such as shape and appearance, that may be useful for solving other related tasks. As a result, the learned model not only inculcates task-bias but also dataset-bias because of its strong reliance on the annotated samples, which also holds true for weakly-supervised models. Acknowledging this, we propose a self-supervised learning framework to disentangle such variations from unlabeled video frames. We leverage the pri…
A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction
National University of Science and Technology "Politehnica" Bucharest（布加勒斯特理工国立大学）；"Simion Stoilow" Institute of Mathematics of the Romanian Academy（罗马尼亚科学院西米翁斯托伊洛夫数学研究所）；NORCE Norwegian Research Centre AS（NORCE挪威研究中心AS公司）
The University of Sheffield（谢菲尔德大学）；University of East Anglia（东英吉利大学）
Magnetic Resonance Imaging (MRI) offers high-resolution \emph{in vivo} imaging and rich functional and anatomical multimodality tissue contrast. In practice, however, there are challenges associated with considerations of scanning costs, patient comfort, and scanning time that constrain how much data can be acquired in clinical or research studies. In this paper, we explore the possibility of generating high-resolution and multimodal images from low-resolution single-modality imagery. We propose the weakly-supervised joint convolutional sparse coding to simultaneously solve the problems of sup…
University of Washington（华盛顿大学）；Facebook Reality Labs Research（Facebook现实实验室研究）
We introduce a novel approach to generate diverse high fidelity texture maps for 3D human meshes in a semi-supervised setup. Given a segmentation mask defining the layout of the semantic regions in the texture map, our network generates high-resolution textures with a variety of styles, that are then used for rendering purposes. To accomplish this task, we propose a Region-adaptive Adversarial Variational AutoEncoder (ReAVAE) that learns the probability distribution of the style of each region individually so that the style of the generated texture can be controlled by sampling from the region…
We study the problem of learning to estimate the 3D object pose from a few labelled examples and a collection of unlabelled data. Our main contribution is a learning framework, neural view synthesis and matching, that can transfer the 3D pose annotation from the labelled to unlabelled images reliably, despite unseen 3D views and nuisance variations such as the object shape, texture, illumination or scene context. In our approach, objects are represented as 3D cuboid meshes composed of feature vectors at each mesh vertex. The model is initialized from a few labelled images and is subsequently u…
$\mathrm{F^2Depth}$: Self-supervised Indoor Monocular Depth Estimation via Optical Flow Consistency and Feature Map Synthesis
Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Qingdao Research Institute of Beihang University（北京航空航天大学青岛研究院）；School of Automation Science and Electrical Engineering, Beihang University（北京航空航天大学自动化科学与电气工程学院）
Shandong University（山东大学）；Baidu Research（百度研究院）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）；Northwestern Polytechnical University（西北工业大学）
Deep convolutional neural network (DCNN) has been successfully applied to depth map super-resolution and outperforms existing methods by a wide margin. However, there still exist two major issues with these DCNN based depth map super-resolution methods that hinder the performance: i) The low-resolution depth maps either need to be up-sampled before feeding into the network or substantial deconvolution has to be used; and ii) The supervision (high-resolution depth maps) is only applied at the end of the network, thus it is difficult to handle large up-sampling factors, such as $\times 8, \times…
Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis
Department of Bioengineering and Imperial-X, Imperial College London（生物工程系和Imperial-X，帝国理工学院伦敦分校）；Department of Bioengineering, Imperial College London（生物工程系，帝国理工学院伦敦分校）；School of Biomedical Engineering, Sun Yat-sen University（生物医学工程学院，中山大学）；Monash Biomedical Imaging, Monash University（莫纳什大学生物医学成像）
