Photoacoustic tomography (PAT) is a newly emerged imaging modality which enables both high optical contrast and acoustic depth of penetration. Reconstructing images of photoacoustic tomography from limited amount of senser data is among one of the major challenges in photoacoustic imaging. Previous works based on deep learning were trained in supervised fashion, which directly map the input partially known sensor data to the ground truth reconstructed from full field of view. Recently, score-based generative models played an increasingly significant role in generative modeling. Leveraging this probabilistic model, we proposed Rotation Consistency Constrained Score-based Generative Model (RCC-SGM), which recovers the PAT images by iterative sampling between Langevin dynamics and a constraint term utilizing the rotation consistency between the images and the measurements. Our proposed method can generalize to different measurement processes (32.29 PSNR with 16 measurements under random sampling, whereas 28.50 for supervised counterpart), while supervised methods need to train on specific inverse mappings.
ShanghaiTech University（上海科技大学）；University of Chinese Academy of Sciences（中国科学院大学）
Photoacoustic imaging (PAI) is a non-invasive imaging modality that detects the ultrasound signal generated from tissue with light excitation. Photoacoustic computed tomography (PACT) uses unfocused large-area light to illuminate the target with ultrasound transducer array for PA signal detection. Limited-view issue could cause a low-quality image in PACT due to the limitation of geometric condition. The model-based method is used to resolve this problem, which contains different regularization. To adapt fast and high-quality reconstruction of limited-view PA data, in this paper, a model-based…
Indian Institute of Space Science and Technology（印度空间科学技术研究院）
Visual Object tracking research has undergone significant improvement in the past few years. The emergence of tracking by detection approach in tracking paradigm has been quite successful in many ways. Recently, deep convolutional neural networks have been extensively used in most successful trackers. Yet, the standard approach has been based on correlation or feature selection with minimal consideration given to motion consistency. Thus, there is still a need to capture various physical constraints through motion consistency which will improve accuracy, robustness and more importantly rotatio…
We present a relocalization pipeline, which combines an absolute pose regression (APR) network with a novel view synthesis based direct matching module, offering superior accuracy while maintaining low inference time. Our contribution is twofold: i) we design a direct matching module that supplies a photometric supervision signal to refine the pose regression network via differentiable rendering; ii) we modify the rotation representation from the classical quaternion to SO(3) in pose regression, removing the need for balancing rotation and translation loss terms. As a result, our network Direc…
MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
Shandong University（山东大学）；AICFVE, Beijing Film Academy（北京电影学院AICFVE）；Tel-Aviv University（特拉维夫大学）；University of Cyprus（塞浦路斯大学）；RISE Research Centre（RISE研究中心）；Edinburgh University（爱丁堡大学）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；CFCS, Peking University（北京大学CFCS）
We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type of transformation (specifically, image rotation) and ask the learner to predict the properties of the transformation. However, the obtained feature representation may contain a large amount of irrelevant information with respect to the main task. To provide further guidance, we force the feature representation of the augmented data to be consistent with tha…
Beijing Institute of Technology（北京理工大学）；QCraft（轻舟智航）；University of Macau（澳门大学）
Monocular 3D object detection has become a mainstream approach in automatic driving for its easy application. A prominent advantage is that it does not need LiDAR point clouds during the inference. However, most current methods still rely on 3D point cloud data for labeling the ground truths used in the training phase. This inconsistency between the training and inference makes it hard to utilize the large-scale feedback data and increases the data collection expenses. To bridge this gap, we propose a new weakly supervised monocular 3D objection detection method, which can train the model with…
Boston University（波士顿大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier using source labels. In semi-supervised domain adaptation (SSDA), when the learner can access few target domain labels, prior approaches have followed UDA theory to use domain alignment for learning. We show that the case of SSDA is different and a good target classifier can be learned without needing alignment. We use self-supervised pretraining (via rotation prediction) and consistency regularization to achieve well…
ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion
School of Computer Science and Technology, Xi'an Jiaotong University（西安交通大学计算机科学与技术学院）；School of Information Engineering, Chang'an University（长安大学信息工程学院）
DUN-SRE: Deep Unrolling Network with Spatiotemporal Rotation Equivariance for Dynamic MRI Reconstruction
University of Nottingham Ningbo China（诺丁汉大学宁波校区）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院）；School of Mathematics and Statistics, Xi’an Jiaotong University（西安交通大学数学与统计学院）
RoES: Rotational Equivariant Selective-frequency Fusion for Multimodal Images
Zhongnan University of Economics and Law（中南财经政法大学）；City University of Macau（澳门城市大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Hubei University（湖北大学）；Xi’an High-tech Research Institute（西安高新技术研究所）；China University of Geosciences (Wuhan)（中国地质大学（武汉））
A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation
Hohai university（河海大学）；School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）；Institute for Infocomm Research (I 2 R), A*STAR（信息通信研究院（I2R），A*STAR）
Baidu Research（百度研究院）；ReLER University of Technology Sydney（悉尼科技大学ReLER）
Compared to 2D object bounding-box labeling, it is very difficult for humans to annotate 3D object poses, especially when depth images of scenes are unavailable. This paper investigates whether we can estimate the object poses effectively when only RGB images and 2D object annotations are given. To this end, we present a two-step pose estimation framework to attain 6DoF object poses from 2D object bounding-boxes. In the first step, the framework learns to segment objects from real and synthetic data in a weakly-supervised fashion, and the segmentation masks will act as a prior for pose estimat…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Proliferation of touch-based devices has made sketch-based image retrieval practical. While many methods exist for sketch-based object detection/image retrieval on small datasets, relatively less work has been done on large (web)-scale image retrieval. In this paper, we present an efficient approach for image retrieval from millions of images based on user-drawn sketches. Unlike existing methods for this problem which are sensitive to even translation or scale variations, our method handles rotation, translation, scale (i.e. a similarity transformation) and small deformations. The object bound…
Semi-Supervised Coupled Thin-Plate Spline Model for Rotation Correction and Beyond
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；Beijing Key Laboratory of Advanced Information Science and Network Technology（先进信息科学与网络技术北京市重点实验室）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）
