Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning. Most approaches regress the full object shape in a canonical pose, possibly extrapolating the occluded parts based on the learned priors. However, their viewpoint invariant technique often discards the unique structures visible from the input images. In contrast, this paper proposes to rely on viewpoint variant reconstructions by merging the visible information from the given views. Our approach is divided into three steps. Starting from the sparse views of the object, we first align them into a common coordinate system by estimating the relative pose between all the pairs. Then, inspired by the traditional voxel carving, we generate an occupancy grid of the object taken from the silhouette on the images and their relative poses. Finally, we refine the initial reconstruction to build a clean 3D model which preserves the details from each viewpoint. To validate the proposed method, we perform a comprehensive evaluation on the ShapeNet reference benchmark in terms of relative pose estimation and 3D shape reconstruction.
Hikvision Research Institute（海康威视研究院）；Zhejiang University（浙江大学）
Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the generalizability of deep neural networks is difficult to control, existing models such as autoencoder do not work well. In this work, we interpret the reconstruction of an image as a divide-and-assemble procedure. Surprisingly, by varying the granularity of division on feature maps, we are able to modulate the reconstruction capability of the model for both normal and abnormal samp…
National Tsing Hua University（国立清华大学）；ASUS AICS（华硕AI研发中心）；Joint Research Center for AI Technology and All Vista Healthcare（AI技术与All Vista Healthcare联合研究中心）；Aeolus Robotics
Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity. We leverage this phenomenon to approximate the scene in a 360-degree image with (H)orizontal-planes and (V)ertical-planes. To this end, we propose an effective divide-and-conquer strategy that divides pixels based on their plane orientation estimation; then, the succeeding instance segmentation module conquers the task of planes clustering more easily in each plane orientation group. Besides, parameters of V-planes depend on camera yaw rotation, but translation-invariant CNNs are less aware of the…
Huazhong University of Science and Technology（华中科技大学）
Accuracy and efficiency are two key problems in large scale incremental Structure from Motion (SfM). In this paper, we propose a unified framework to divide the image set into clusters suitable for reconstruction as well as find multiple reliable and stable starting points. Image partitioning performs in two steps. First, some small image groups are selected at places with high image density, and then all the images are clustered according to their optimal reconstruction paths to these image groups. This promises that the scene is always reconstructed from dense places to sparse areas, which c…
Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires. In traditional CS-MRI inversion methods, the fact that the energy within the Fourier measurement domain is distributed non-uniformly is often neglected during reconstruction. As a result, more densely sampled low-frequency information tends to dominate penalization schemes for reconstructing MRI at the expense of high-frequency details. In this paper, we propose a new framework for CS-MRI inversion in which we decompose…
Transformers are becoming increasingly popular due to their superior performance over conventional convolutional neural networks(CNNs). However, transformers usually require a much larger amount of memory to train than CNNs, which prevents their application in many low resource settings. Local learning, which divides the network into several distinct modules and trains them individually, is a promising alternative to the end-to-end (E2E) training approach to reduce the amount of memory for training and to increase parallelism. This paper is the first to apply Local Learning on transformers for…
Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images
United Imaging Intelligence（联影智能）；State University of New York at Buffalo（纽约州立大学布法罗分校）；Peking University（北京大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Vanderbilt University（范德堡大学）
We consider the problem of reconstructing an image from compressive measurements using a multi-resolution grid. In this context, the reconstructed image is divided into multiple regions, each one with a different resolution. This problem arises in situations where the image to reconstruct contains a certain region of interest (RoI) that is more important than the rest. Through a theoretical analysis and simulation experiments we show that the multi-resolution reconstruction provides a higher quality of the RoI compared to the traditional single-resolution approach.
Peking University（北京大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
While Structure from Motion (SfM) achieves great success in 3D reconstruction, it still meets challenges on large scale scenes. In this work, large scale SfM is deemed as a graph problem, and we tackle it in a divide-and-conquer manner. Firstly, the images clustering algorithm divides images into clusters with strong connectivity, leading to robust local reconstructions. Then followed with an image expansion step, the connection and completeness of scenes are enhanced by expanding along with a maximum spanning tree. After local reconstructions, we construct a minimum spanning tree (MinST) to f…
Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
Shenzhen Graduate School, Peking University（北京大学深圳研究生院）；Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东省超高清沉浸式媒体技术重点实验室）
Hong Kong Baptist University（香港浸会大学）；Michigan State University（密歇根州立大学）
State-of-the-art face recognition systems are based on deep (convolutional) neural networks. Therefore, it is imperative to determine to what extent face templates derived from deep networks can be inverted to obtain the original face image. In this paper, we study the vulnerabilities of a state-of-the-art face recognition system based on template reconstruction attack. We propose a neighborly de-convolutional neural network (\textit{NbNet}) to reconstruct face images from their deep templates. In our experiments, we assumed that no knowledge about the target subject and the deep network are a…
University of Cambridge（剑桥大学）；KTH – Royal Institute of Technology（瑞典皇家理工学院）
In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning. Therefore, it is imperative to develop unsupervised learning protocols that are competitive with supervised approaches in performance. Motivated by the maximum-likelihood principle, we propose an unsupervised learning framework for solving ill-posed inverse problems. Instead of seeking pixel-wise proximity between the reconstructed and the ground-truth images, the proposed approach learns an iterative recons…
Center for Visual Information Technology, IIIT Hyderabad（海得拉巴国际信息技术研究所视觉信息技术中心）；Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）
Several methods have been proposed for large-scale 3D reconstruction from large, unorganized image collections. A large reconstruction problem is typically divided into multiple components which are reconstructed independently using structure from motion (SFM) and later merged together. Incremental SFM methods are most popular for the basic structure recovery of a single component. They are robust and effective but are strictly sequential in nature. We present a multistage approach for SFM reconstruction of a single component that breaks the sequential nature of the incremental SFM methods. Ou…
Monocular 3D facial shape reconstruction from a single 2D facial image has been an active research area due to its wide applications. Inspired by the success of deep neural networks (DNN), we propose a DNN-based approach for End-to-End 3D FAce Reconstruction (UH-E2FAR) from a single 2D image. Different from recent works that reconstruct and refine the 3D face in an iterative manner using both an RGB image and an initial 3D facial shape rendering, our DNN model is end-to-end, and thus the complicated 3D rendering process can be avoided. Moreover, we integrate in the DNN architecture two compone…
The University of Hong Kong（香港大学）；Tencent Games（腾讯游戏）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Texas A&M University（德克萨斯农工大学）
We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. Recent advances in neural rendering based reconstruction have achieved compelling results. However, these methods are limited to objects with closed surfaces since they adopt Signed Distance Function (SDF) as surface representation which requires the target shape to be divided into inside and outside. In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF represe…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；China Electronic Science and Technology Network Information Security Co., Ltd.（中国电子科技网络信息安全有限公司）
For a better performance in single image super-resolution(SISR), we present an image super-resolution algorithm based on adaptive dense connection (ADCSR). The algorithm is divided into two parts: BODY and SKIP. BODY improves the utilization of convolution features through adaptive dense connections. Also, we develop an adaptive sub-pixel reconstruction layer (AFSL) to reconstruct the features of the BODY output. We pre-trained SKIP to make BODY focus on high-frequency feature learning. The comparison of PSNR, SSIM, and visual effects verify the superiority of our method to the state-of-the-ar…
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Electronic Information, Wuhan University（武汉大学电子信息学院）；State Key Lab. of LIESMARS, Wuhan University（武汉大学LIESMARS国家重点实验室）；Institute for Math & AI, Wuhan University（武汉大学数学与人工智能研究院）
Traditional dictionary learning based CT reconstruction methods are patch-based and the features learned with these methods often contain shifted versions of the same features. To deal with these problems, the convolutional sparse coding (CSC) has been proposed and introduced into various applications. In this paper, inspired by the successful applications of CSC in the field of signal processing, we propose a novel sparse-view CT reconstruction method based on CSC with gradient regularization on feature maps. By directly working on whole image, which need not to divide the image into overlapp…
ClipGStream: Clip-Stream Gaussian Splatting for Any Length and Any Motion Multi-View Dynamic Scene Reconstruction
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东超高清沉浸式媒体技术省重点实验室）；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）；Pengcheng Laboratory（鹏城实验室）；Peking University（北京大学）；MIGU Video Co., Ltd.（MIGU视频有限公司）
The Hong Kong University of Science and Technology（香港科技大学）；Kwai Inc.（快手公司）
We present a novel end-to-end framework named as GSNet (Geometric and Scene-aware Network), which jointly estimates 6DoF poses and reconstructs detailed 3D car shapes from single urban street view. GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass. Extensive experiments show that our diverse feature extraction and fusion scheme can greatly improve model performance. Based on a divide-and-conquer 3D shape representation strategy, GSNet reconstructs 3D vehicle shape with great detail (1352 vertices and 2700…
Institute for Computer Science and Control, Hungarian Academy of Sciences（匈牙利科学院计算机科学与控制研究所）
In this paper, we propose a novel image denoising algorithm using collaborative support-agnostic sparse reconstruction. An observed image is first divided into patches. Similarly structured patches are grouped together to be utilized for collaborative processing. In the proposed collaborative schemes, similar patches are assumed to share the same support taps. For sparse reconstruction, the likelihood of a tap being active in a patch is computed and refined through a collaboration process with other similar patches in the same group. This provides very good patch support estimation, hence enha…
Surgical instrument tracking is an active research area that can provide surgeons feedback about the location of their tools relative to anatomy. Recent tracking methods are mainly divided into two parts: segmentation and object detection. However, both can only predict 2D information, which is limiting for application to real-world surgery. An accurate 3D surgical instrument model is a prerequisite for precise predictions of the pose and depth of the instrument. Recent single-view 3D reconstruction methods are only used in natural object reconstruction and do not achieve satisfying reconstruc…
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；CRRC Academy Co., Ltd.（中车研究院有限公司）；School of Computer Science, Sun Yat-sen University（中山大学计算机学院）
Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received significant interest for accelerating magnetic resonance imaging (MRI) acquisition and reconstruction strategies. A number of ideas inspired by deep learning techniques for computer vision and image processing have been successfully applied to nonlinear image reconstruction in the spirit of compressed sensing for accelerated MRI. Given the rapidly growing nature of the field, it is imperative to consolidate and summarize the large number of deep learning method…
Shenzhen University（深圳大学）；University of Delaware（特拉华大学）；Chongqing University（重庆大学）；Chongqing University of Science and Technology（重庆科技大学）
In this paper, we propose a new GPU implementation of the Katsevich algorithm for helical CT reconstruction. Our implementation divides the sinograms and reconstructs the CT images pitch by pitch. By utilizing the periodic properties of the parameters of the Katsevich algorithm, our method only needs to calculate these parameters once for all the pitches and so has lower GPU-memory burdens and is very suitable for deep learning. By embedding our implementation into the network, we propose an end-to-end deep network for the high pitch helical CT reconstruction with sparse detectors. Since our n…
GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
The University of Hong Kong（香港大学）；Hong Kong University of Science and Technology（香港科技大学）；Nanyang Technological University（南洋理工大学）；City University of Hong Kong（香港城市大学）；Texas A&M University（德克萨斯农工大学）
本文提出 GausSurf，结合多视角 MVS 几何引导与法线先验，分别优化纹理丰富和无纹理区域的 3D Gaussian Splatting 表面重建，在质量与速度上超越现有方法。
Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；CIIRC – Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague（布拉格捷克技术大学信息学、机器人与控制论研究所）；Microsoft（微软）；ETH Zurich（苏黎世联邦理工学院）；Facebook AI Research（Facebook人工智能研究院）
Narrated instructional videos often show and describe manipulations of similar objects, e.g., repairing a particular model of a car or laptop. In this work we aim to reconstruct such objects and to localize associated narrations in 3D. Contrary to the standard scenario of instance-level 3D reconstruction, where identical objects or scenes are present in all views, objects in different instructional videos may have large appearance variations given varying conditions and versions of the same product. Narrations may also have large variation in natural language expressions. We address these chal…
Harbin Institute of Technology（哈尔滨工业大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）；Nanjing Medical University（南京医科大学）
The core problem of Magnetic Resonance Imaging (MRI) is the trade off between acceleration and image quality. Image reconstruction and super-resolution are two crucial techniques in Magnetic Resonance Imaging (MRI). Current methods are designed to perform these tasks separately, ignoring the correlations between them. In this work, we propose an end-to-end task transformer network (T$^2$Net) for joint MRI reconstruction and super-resolution, which allows representations and feature transmission to be shared between multiple task to achieve higher-quality, super-resolved and motion-artifacts-fr…
University College London（伦敦大学学院）；King’s College London（伦敦国王学院）
Quality control (QC) in medical image analysis is time-consuming and laborious, leading to increased interest in automated methods. However, what is deemed suitable quality for algorithmic processing may be different from human-perceived measures of visual quality. In this work, we pose MR image quality assessment from an image reconstruction perspective. We train Bayesian CNNs using a heteroscedastic uncertainty model to recover clean images from noisy data, providing measures of uncertainty over the predictions. This framework enables us to divide data corruption into learnable and non-learn…
Xiamen University（厦门大学）；University of Iowa（爱荷华大学）；Xiamen University of Technology（厦门理工学院）
Objective: Improve the reconstructed image with fast and multi-class dictionaries learning when magnetic resonance imaging is accelerated by undersampling the k-space data. Methods: A fast orthogonal dictionary learning method is introduced into magnetic resonance image reconstruction to providing adaptive sparse representation of images. To enhance the sparsity, image is divided into classified patches according to the same geometrical direction and dictionary is trained within each class. A new sparse reconstruction model with the multi-class dictionaries is proposed and solved using a fast …
University of Electronic Science and Technology of China（电子科技大学）；Shanghai Jiao Tong University（上海交通大学）
Most compressive sensing (CS) reconstruction methods can be divided into two categories, i.e. model-based methods and classical deep network methods. By unfolding the iterative optimization algorithm for model-based methods onto networks, deep unfolding methods have the good interpretation of model-based methods and the high speed of classical deep network methods. In this paper, to solve the visual image CS problem, we propose a deep unfolding model dubbed AMP-Net. Rather than learning regularization terms, it is established by unfolding the iterative denoising process of the well-known appro…
New Mexico Consortium（新墨西哥联盟）；University of California, Berkeley（加州大学伯克利分校）；University of Michigan（密歇根大学）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
In sparse coding it is common to tile an image into nonoverlapping patches, and then use a dictionary to create a sparse representation of each tile independently. In this situation, the overcompleteness of the dictionary is the number of dictionary elements divided by the patch size. In deconvolutional neural networks (DCNs), dictionaries learned on nonoverlapping tiles are replaced by a family of convolution kernels. Hence adjacent points in the feature maps (V1 layers) have receptive fields in the image that are translations of each other. The translational distance is determined by the dim…
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）；Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；Terminus Group（特斯联集团）
Federated learning (FL) can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction by enabling multiple institutions to collaborate without needing to aggregate local data. However, the domain shift caused by different MR imaging protocols can substantially degrade the performance of FL models. Recent FL techniques tend to solve this by enhancing the generalization of the global model, but they ignore the domain-specific features, which may contain important information about the device properties and be useful for local reconstruction. In this paper, we…
Statistical image reconstruction (SIR) methods have shown potential to substantially improve the image quality of low-dose X-ray computed tomography (CT) as compared to the conventional filtered back-projection (FBP) method for various clinical tasks. According to the maximum a posterior (MAP) estimation, the SIR methods can be typically formulated by an objective function consisting of two terms: (1) data-fidelity (or equivalently, data-fitting or data-mismatch) term modeling the statistics of projection measurements, and (2) regularization (or equivalently, prior or penalty) term reflecting …
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；University of Electronic Science and Technology of China（电子科技大学）；Inception Institute of Artificial Intelligence（人工智能起源研究所）
Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration by obtaining multiple undersampled images simultaneously through parallel imaging has always been the subject of research. In this paper, we propose the Dual-Octave Convolution (Dual-OctConv), which is capable of learning multi-scale spatial-frequency features from both real and imaginary components, for fast parallel MR image reconstruction. By reformulating the complex operations using octave convolutions, our model shows a strong ability to capture richer representations of MR images, while at t…
