The ability to decompose scenes into their object components is a desired property for autonomous agents, allowing them to reason and act in their surroundings. Recently, different methods have been proposed to learn object-centric representations from data in an unsupervised manner. These methods often rely on latent representations learned by deep neural networks, hence requiring high computational costs and large amounts of curated data. Such models are also difficult to interpret. To address these challenges, we propose the Phase-Correlation Decomposition Network (PCDNet), a novel model that decomposes a scene into its object components, which are represented as transformed versions of a set of learned object prototypes. The core building block in PCDNet is the Phase-Correlation Cell (PC Cell), which exploits the frequency-domain representation of the images in order to estimate the transformation between an object prototype and its transformed version in the image. In our experiments, we show how PCDNet outperforms state-of-the-art methods for unsupervised object discovery and segmentation on simple benchmark datasets and on more challenging data, while using a small number of learnable parameters and being fully interpretable.
University of British Columbia（不列颠哥伦比亚大学）；Borealis AI；Vector Institute for AI（Vector AI研究所）
Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a novel spatio-temporal iterative inference framework that is powerful enough to jointly model complex multi-object representations and explicit temporal dependencies between latent variables across frames. This is achieved by leveraging 2D-LSTM, temporally conditioned inference and generation within the iterative amortized inference for posterior refinement. Our…
Many seemingly unrelated computer vision tasks can be viewed as a special case of image decomposition into separate layers. For example, image segmentation (separation into foreground and background layers); transparent layer separation (into reflection and transmission layers); Image dehazing (separation into a clear image and a haze map), and more. In this paper we propose a unified framework for unsupervised layer decomposition of a single image, based on coupled "Deep-image-Prior" (DIP) networks. It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficien…
The University of Tokyo（东京大学）；RIKEN AIP（理化学研究所先进智能项目中心）
Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent part parsing. In this paper, we propose PPD (unsupervised Pose-aware Part Decomposition) to address a novel setting that explicitly targets man-made articulated objects with mechanical joints, considering the part poses. We show that category-common prior learning for both part shapes and poses facilitates the unsupervised learning of (1) part decomposition …
Simon Fraser University（西蒙弗雷泽大学）；Microsoft Research（微软研究院）
We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos online, which exhibit large illumination variations that make them suitable for training of reflectance separation and can facilitate object-level decomposition. The main contribution of our approach is a proposed image representation based on local color distributions that allows training to be insensitive to the local misalignments of multi-view images. In…
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building blocks share meaningful properties, interactions and other regularities across scenes, such decompositions can simplify reasoning and facilitate imagination of novel scenarios. In particular, representing perceptual observations in terms of entities should improve data efficiency and transfer performance on a wide range of tasks. Thus we need models capable of discovering useful decompositions of scenes by identifying units with such regularities and representing…
We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a spatial mixture model where each component corresponds to one object. To model the spatial mixture model on point clouds, we derive the Chamfer Mixture Loss, which fits naturally into our variational training pipeline. Moreover, we adopt an object-specification scheme that describes each object's location relative to its local voxel grid cell. Such a scheme…
Beihang University（北京航空航天大学）；Tencent（腾讯）；University of Amsterdam（阿姆斯特丹大学）；Peng Cheng Laboratory（鹏城实验室）
Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional methods introduce various priors to constrain the solution, yet with limited performance. Meanwhile, the problem is typically solved by supervised learning methods, which is actually not an ideal solution since obtaining ground truth reflectance and shading for massive general natural scenes is challenging and even impossible. In this paper, we propose a nove…
Georgia Institute of Technology（佐治亚理工学院）；Apple（苹果公司）
Unsupervised pixel-level defective region segmentation is an important task in image-based anomaly detection for various industrial applications. The state-of-the-art methods have their own advantages and limitations: matrix-decomposition-based methods are robust to noise but lack complex background image modeling capability; representation-based methods are good at defective region localization but lack accuracy in defective region shape contour extraction; reconstruction-based methods detected defective region match well with the ground truth defective region shape contour but are noisy. To …
To help agents reason about scenes in terms of their building blocks, we wish to extract the compositional structure of any given scene (in particular, the configuration and characteristics of objects comprising the scene). This problem is especially difficult when scene structure needs to be inferred while also estimating the agent's location/viewpoint, as the two variables jointly give rise to the agent's observations. We present an unsupervised variational approach to this problem. Leveraging the shared structure that exists across different scenes, our model learns to infer two sets of lat…
NTT Human Informatics Laboratories（NTT人类信息学实验室）；NTT Communication Science Laboratories（NTT通信科学实验室）
Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albedo and shade in general scenes. Conversely, unsupervised learning methods are currently underperforming supervised learning methods since there are no criteria for solving the ill-posed problems. Recently, light detection and ranging (LiDAR) is widely used due to its ability to make highly precise distance measurements. Thus, we have focused on the utilization…
A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives rise to them. We instead propose to model a video as the view seen while moving through a scene with multiple 3D objects and a 3D background. Our model is trained from monocular videos without any supervision, yet learns to generate coherent 3D scenes containing several moving objects. We conduct detailed experiments on two datasets, going beyond the visual…
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Yale-NUS College（耶鲁-新加坡国立大学学院）
Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This inevitably leads to over enhancement and saturation in bright regions, such as those regions affected by light effects (glare, floodlight, etc). To address this problem, we need to suppress the light effects in bright regions while, at the same time, boosting the intensity of dark regions. With this idea in mind, we introduce an unsupervised method that integrates a layer decomposition network and a light-…
Facebook AI Research（脸书人工智能研究院）；Tel Aviv University（特拉维夫大学）
Linking between two data sources is a basic building block in numerous computer vision problems. In this paper, we set to answer a fundamental cognitive question: are prior correspondences necessary for linking between different domains? One of the most popular methods for linking between domains is Canonical Correlation Analysis (CCA). All current CCA algorithms require correspondences between the views. We introduce a new method Unsupervised Correlation Analysis (UCA), which requires no prior correspondences between the two domains. The correlation maximization term in CCA is replaced by a c…
Facebook AI Research（脸书人工智能研究院）；LIGM (UMR 8049) - École des Ponts, UPE（巴黎东大学桥梁学校信息、高斯与数学实验室（UMR 8049））
Deep image generation is becoming a tool to enhance artists and designers creativity potential. In this paper, we aim at making the generation process more structured and easier to interact with. Inspired by vector graphics systems, we propose a new deep image reconstruction paradigm where the outputs are composed from simple layers, defined by their color and a vector transparency mask. This presents a number of advantages compared to the commonly used convolutional network architectures. In particular, our layered decomposition allows simple user interaction, for example to update a given ma…
University of California, Berkeley（加州大学伯克利分校）；Google（谷歌）
We describe a method to extract persistent elements of a dynamic scene from an input video. We represent each scene element as a \emph{Deformable Sprite} consisting of three components: 1) a 2D texture image for the entire video, 2) per-frame masks for the element, and 3) non-rigid deformations that map the texture image into each video frame. The resulting decomposition allows for applications such as consistent video editing. Deformable Sprites are a type of video auto-encoder model that is optimized on individual videos, and does not require training on a large dataset, nor does it rely on …
Mila-Quebec AI Institute, Canada（魁北克AI研究所）；Samsung - SAIT AI Lab, Montreal, Canada（三星SAIT人工智能实验室）；University of Montreal, Canada（蒙特利尔大学）；Institute of Science and Technology Austria（奥地利科学与技术研究所）；National University of Singapore（新加坡国立大学）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）；KU Leuven（鲁汶大学）；University of Tübingen（图宾根大学）
Humans perceive the 3D world as a set of distinct objects that are characterized by various low-level (geometry, reflectance) and high-level (connectivity, adjacency, symmetry) properties. Recent methods based on convolutional neural networks (CNNs) demonstrated impressive progress in 3D reconstruction, even when using a single 2D image as input. However, the majority of these methods focuses on recovering the local 3D geometry of an object without considering its part-based decomposition or relations between parts. We address this challenging problem by proposing a novel formulation that allo…
Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；School of Information Science and Engineering, Wuhan University of Science and Technology（武汉科技大学信息科学与工程学院）；School of Cyber Science and Engineering, Wuhan University（武汉大学网络空间安全学院）；School of Electronic Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes. In this paper, we propose a generative latent variable model, called SPACE, that provides a unified probabilistic modeling framework that combines the best of spatial-attention and scene-mixture approaches. SPACE can e…
LIGM, École des Ponts, Univ Gustave Eiffel, CNRS（LIGM，巴黎高科路桥学校，古斯塔夫·埃菲尔大学，法国国家科学研究中心）；Inria and DIENS (ENS-PSL, CNRS, Inria)（法国国家信息与自动化研究所和DIENS（巴黎高等师范学院-巴黎文理研究大学，法国国家科学研究中心，法国国家信息与自动化研究所））；Center for Data Science, New York University（纽约大学数据科学中心）
We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. Contrary to recent approaches that model image layers with autoencoder networks, we represent them as explicit transformations of a small set of prototypical images. Our model has three main components: (i) a set of object prototypes in the form of learnable images with a transparency channel, which we refer to as sprites; (ii) differentiable parametric functions predicting occlusions and transformation parameters necessary to instantiate the sprites in a given image; (ii…
National Technological University of Athens（雅典国家技术大学）
In this paper, we scrutinize the effectiveness of various clustering techniques, investigating their applicability in Cultural Heritage monitoring applications. In the context of this paper, we detect the level of decomposition and corrosion on the walls of Saint Nicholas fort in Rhodes utilizing hyperspectral images. A total of 6 different clustering approaches have been evaluated over a set of 14 different orthorectified hyperspectral images. Experimental setup in this study involves K-means, Spectral, Meanshift, DBSCAN, Birch and Optics algorithms. For each of these techniques we evaluate i…
ETH Zürich（苏黎世联邦理工学院）；Unity Technologies（Unity科技公司）；KU Leuven（鲁汶大学）
Machine learning based Single Image Intrinsic Decomposition (SIID) methods decompose a captured scene into its albedo and shading images by using the knowledge of a large set of known and realistic ground truth decompositions. Collecting and annotating such a dataset is an approach that cannot scale to sufficient variety and realism. We free ourselves from this limitation by training on unannotated images. Our method leverages the observation that two images of the same scene but with different lighting provide useful information on their intrinsic properties: by definition, albedo is invarian…
Representing a 3D shape with a set of primitives can aid perception of structure, improve robotic object manipulation, and enable editing, stylization, and compression of 3D shapes. Existing methods either use simple parametric primitives or learn a generative shape space of parts. Both have limitations: parametric primitives lead to coarse approximations, while learned parts offer too little control over the decomposition. We instead propose to decompose shapes using a library of 3D parts provided by the user, giving full control over the choice of parts. The library can contain parts with hi…
The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has received significantly less attention. In this paper, we propose an unsupervised approach to object part discovery and segmentation and make three contributions. First, we construct a proxy task through a set of objectives that encourages the model to learn a meaningful decomposition of the image into its parts. Secondly, prior work argues for reconstructin…
In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains. We formally demonstrate this hypothesis and, aiming at achieving an optimal alignment in practical cases, we adopt a more principled strategy which, differently from the current Euclidean approaches, deploys alignment along geodesics. Our pipeline can be implemented by adding to the standard classification loss (on the labeled source domai…
Unsupervised Hyperspectral and Multispectral Image Blind Fusion Based on Deep Tucker Decomposition Network with Spatial-Spectral Manifold Learning
School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST)（南京理工大学计算机科学与工程学院）；Geological Exploration Technology Institute of Jiangsu Province（江苏省地质勘查技术院）；Jiangsu Province Engineering Research Center of Airborne Detecting and Intelligent Perceptive Technology（江苏省机载探测与智能感知技术工程研究中心）
We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision. Most existing methods on scene decomposition lack one or more of these characteristics, due to the fundamental challenge in integrating the complex 3D-to-2D image formation process into powerful inference schemes like deep networks. In this paper, we propose unsupervised discovery of Object Radiance Fields (uORF), integrating recent progresses in neural 3D sc…
Portrait images often suffer from undesirable shadows cast by casual objects or even the face itself. While existing methods for portrait shadow removal require training on a large-scale synthetic dataset, we propose the first unsupervised method for portrait shadow removal without any training data. Our key idea is to leverage the generative facial priors embedded in the off-the-shelf pretrained StyleGAN2. To achieve this, we formulate the shadow removal task as a layer decomposition problem: a shadowed portrait image is constructed by the blending of a shadow image and a shadow-free image. W…
University of Pennsylvania（宾夕法尼亚大学）；Perelman School of Medicine（佩雷尔曼医学院）；Department of Radiology（放射科）；Center for Biomedical Image Computing and Analytics (CBICA)（生物医学图像计算与分析中心（CBICA））
A novel unsupervised deep learning method is developed to identify individual-specific large scale brain functional networks (FNs) from resting-state fMRI (rsfMRI) in an end-to-end learning fashion. Our method leverages deep Encoder-Decoder networks and conventional brain decomposition models to identify individual-specific FNs in an unsupervised learning framework and facilitate fast inference for new individuals with one forward pass of the deep network. Particularly, convolutional neural networks (CNNs) with an Encoder-Decoder architecture are adopted to identify individual-specific FNs fro…
"Self-training" has become a dominant method for semantic segmentation via unsupervised domain adaptation (UDA). It creates a set of pseudo labels for the target domain to give explicit supervision. However, the pseudo labels are noisy, sparse and do not provide any information about inter-pixel correlations. We regard inter-pixel correlation quite important because semantic segmentation is a task of predicting highly structured pixel-level outputs. Therefore, in this paper, we propose a method of transferring the inter-pixel correlations from the source domain to the target domain via a self-…
LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
Shanghai Jiao Tong University（上海交通大学）；Megvii Technology（旷视科技）；Sichuan University（四川大学）；Southwest Jiaotong University（西南交通大学）；University of Electronic Science and Technology of China（电子科技大学）
National University of Defense Technology（国防科技大学）；Shandong University（山东大学）；Simon Fraser University（西蒙弗雷泽大学）
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field deco…
Spectral clustering is one of the most popular clustering approaches with the capability to handle some challenging clustering problems. Most spectral clustering methods provide a nonlinear map from the data manifold to a subspace. Only a little work focuses on the explicit linear map which can be viewed as the unsupervised distance metric learning. In practice, the selection of the affinity matrix exhibits a tremendous impact on the unsupervised learning. While much success of affinity learning has been achieved in recent years, some issues such as noise reduction remain to be addressed. In t…
In this paper, we introduce an unsupervised learning approach to automatically discover, summarize, and manipulate artistic styles from large collections of paintings. Our method is based on archetypal analysis, which is an unsupervised learning technique akin to sparse coding with a geometric interpretation. When applied to deep image representations from a collection of artworks, it learns a dictionary of archetypal styles, which can be easily visualized. After training the model, the style of a new image, which is characterized by local statistics of deep visual features, is approximated by…
Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models
Research Laboratory of Electronics, MIT, Cambridge, MA 02139, USA（MIT电子研究实验室）；Department of Physics, Massachusetts Institute of Technology, MIT, Cambridge, MA, USA（麻省理工学院物理系）；NSF AI Institute for Artificial Intelligence（国家科学基金会人工智能与基本相互作用研究所）；Kempner Institute, Harvard University, Cambridge, MA, USA（哈佛大学 Kempner 院）；Google DeepMind, Mountain View, CA, USA（Google DeepMind）；School of Computer Science, Georgia Institute of Technology, Atlanta, USA（佐治亚理工学院计算机科学系）
Unsupervised Deformable Image Registration with Local-Global Attention and Image Decomposition
Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术研究所）；National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院）；Department of Radiology, Peking University Third Hospital（北京大学第三医院放射科）；Department of Pediatrics, Peking University First Hospital（北京大学第一医院儿科）；Pediatric Epilepsy Center, Peking University First Hospital（北京大学第一医院儿童癫痫中心）；School of Biological Science and Medical Engineering, Southeast University（东南大学生物科学与医学工程学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
University of Electronic Science and Technology of China（电子科技大学）；Oregon State University（俄勒冈州立大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
Image denoising is often empowered by accurate prior information. In recent years, data-driven neural network priors have shown promising performance for RGB natural image denoising. Compared to classic handcrafted priors (e.g., sparsity and total variation), the "deep priors" are learned using a large number of training samples -- which can accurately model the complex image generating process. However, data-driven priors are hard to acquire for hyperspectral images (HSIs) due to the lack of training data. A remedy is to use the so-called unsupervised deep image prior (DIP). Under the unsuper…
Di$^2$CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer
Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Department of Automation, Tsinghua University（清华大学自动化系）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）
State Key Laboratory of Virtual Reality Technology and Systems（虚拟现实技术与系统全国重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机学院）
Many real world vision tasks, such as reflection removal from a transparent surface and intrinsic image decomposition, can be modeled as single image layer separation. However, this problem is highly ill-posed, requiring accurately aligned and hard to collect triplet data to train the CNN models. To address this problem, this paper proposes an unsupervised method that requires no ground truth data triplet in training. At the core of the method are two assumptions about data distributions in the latent spaces of different layers, based on which a novel unsupervised layer separation pipeline can…
Snap Inc.（Snap公司）；University of Trento（特伦托大学）；KAUST（阿卜杜拉国王科技大学）
We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects. Our method learns the 3D structure and dynamics of objects solely from single-view RGB videos, and can decompose them into semantically meaningful parts that can be tracked and animated. Using a 3D autodecoder framework, paired with a keypoint estimator via a differentiable PnP algorithm, our model learns the underlying object geometry and parts decomposition in an entirely unsupervised manner. This allows it to perform 3D segmentation, 3D keypoint estimation, novel view synthesis, and animation. We prim…
An important goal across most scientific fields is the discovery of causal structures underling a set of observations. Unfortunately, causal discovery methods which are based on correlation or mutual information can often fail to identify causal links in systems which exhibit dynamic relationships. Such dynamic systems (including the famous coupled logistic map) exhibit `mirage' correlations which appear and disappear depending on the observation window. This means not only that correlation is not causation but, perhaps counter-intuitively, that causation may occur without correlation. In this…
University of Southern California（南加州大学）；Army Research Laboratory（陆军研究实验室）
An unsupervised online object tracking method that exploits both foreground and background correlations is proposed and named UHP-SOT (Unsupervised High-Performance Single Object Tracker) in this work. UHP-SOT consists of three modules: 1) appearance model update, 2) background motion modeling, and 3) trajectory-based box prediction. A state-of-the-art discriminative correlation filters (DCF) based tracker is adopted by UHP-SOT as the first module. We point out shortcomings of using the first module alone such as failure in recovering from tracking loss and inflexibility in object box adaptati…
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Unsupervised cross-modal hashing is more flexible and applicable than supervised methods, since no intensive labeling work is involved. However, existing unsupervised methods learn hashing functions by preserving inter and intra correlations, while ignoring the underlying manifold structure across different modalities, which is extremely helpful to capture meaningful nearest neighbors of different modalities for cross-modal retrie…
This paper addresses the problem of 2D pose representation during unsupervised 2D to 3D pose lifting to improve the accuracy, stability and generalisability of 3D human pose estimation (HPE) models. All unsupervised 2D-3D HPE approaches provide the entire 2D kinematic skeleton to a model during training. We argue that this is sub-optimal and disruptive as long-range correlations are induced between independent 2D key points and predicted 3D ordinates during training. To this end, we conduct the following study. With a maximum architecture capacity of 6 residual blocks, we evaluate the performa…
