PyTorchKR Papers

최신 논문

총 670편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2208.13935공식 코드 · Papers with Code

CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial Odometry

Learning-based visual ego-motion estimation is promising yet not ready for navigating agile mobile robots in the real world. In this article, we propose CUAHN-VIO, a robust and efficient monocular visual-inertial odometry (VIO) designed for micro aerial vehicles (MAVs) equipped with a downward-facing camera. The vision frontend is a content-and-uncertainty-aware homography network (CUAHN) that is robust to non-homography image content and failure cases of network prediction. It not only predicts the homography transformation but also estimates its uncertainty. The training is self-supervised, so that it does not require ground truth that is often difficult to obtain. The network has good generalization that enables "plug-and-play" deployment in new environments without fine-tuning. A lightweight extended Kalman filter (EKF) serves as the VIO backend and utilizes the mean prediction and variance estimation from the network for visual measurement updates. CUAHN-VIO is evaluated on a high-speed public dataset and shows rivaling accuracy to state-of-the-art (SOTA) VIO approaches. Thanks to the robustness to motion blur, low network inference time (~23ms), and stable processing latency (~26ms), CUAHN-VIO successfully runs onboard an Nvidia Jetson TX2 embedded processor to navigate a fast autonomous MAV.

arXiv:2208.09463공식 코드 · Papers with Code

Temporal View Synthesis of Dynamic Scenes through 3D Object Motion Estimation with Multi-Plane Images

The challenge of graphically rendering high frame-rate videos on low compute devices can be addressed through periodic prediction of future frames to enhance the user experience in virtual reality applications. This is studied through the problem of temporal view synthesis (TVS), where the goal is to predict the next frames of a video given the previous frames and the head poses of the previous and the next frames. In this work, we consider the TVS of dynamic scenes in which both the user and objects are moving. We design a framework that decouples the motion into user and object motion to effectively use the available user motion while predicting the next frames. We predict the motion of objects by isolating and estimating the 3D object motion in the past frames and then extrapolating it. We employ multi-plane images (MPI) as a 3D representation of the scenes and model the object motion as the 3D displacement between the corresponding points in the MPI representation. In order to handle the sparsity in MPIs while estimating the motion, we incorporate partial convolutions and masked correlation layers to estimate corresponding points. The predicted object motion is then integrated with the given user or camera motion to generate the next frame. Using a disocclusion infilling module, we synthesize the regions uncovered due to the camera and object motion. We develop a new synthetic dataset for TVS of dynamic scenes consisting of 800 videos at full HD resolution. We show through experiments on our dataset and the MPI Sintel dataset that our model outperforms all the competing methods in the literature.

arXiv:2208.08645공식 코드 · Papers with Code

Visual Pursuit Control based on Gaussian Processes with Switched Motion Trajectories

This paper considers a scenario of pursuing a moving target that may switch behaviors due to external factors in a dynamic environment by motion estimation using visual sensors. First, we present an improved Visual Motion Observer with switched Gaussian Process models for an extended class of target motion profiles. We then propose a pursuit control law with an online method to estimate the switching behavior of the target by the GP model uncertainty. Next, we prove ultimate boundedness of the control and estimation errors for the switch in target behavior with high probability. Finally, a Digital Twin simulation demonstrates the effectiveness of the proposed switching estimation and control law to prove applicability to real world scenarios.

arXiv:2208.06678

A new way of video compression via forward-referencing using deep learning

To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can efficiently exploit the translation motion of the moving objects, it is susceptible to other types of affine motion and object occlusion/deocclusion. Recently, deep learning has been used to model the high-level structure of human pose in specific actions from short videos and then generate virtual frames in future time by predicting the pose using a generative adversarial network (GAN). Therefore, modelling the high-level structure of human pose is able to exploit semantic correlation by predicting human actions and determining its trajectory. Video surveillance applications will benefit as stored big surveillance data can be compressed by estimating human pose trajectories and generating future frames through semantic correlation. This paper explores a new way of video coding by modelling human pose from the already-encoded frames and using the generated frame at the current time as an additional forward-referencing frame. It is expected that the proposed approach can overcome the limitations of the traditional backward-referencing frames by predicting the blocks containing the moving objects with lower residuals. Experimental results show that the proposed approach can achieve on average up to 2.83 dB PSNR gain and 25.93\% bitrate savings for high motion video sequences

arXiv:2208.03873공식 코드 · Papers with Code

CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships between Chest X-Rays

Despite the progress in utilizing deep learning to automate chest radiograph interpretation and disease diagnosis tasks, change between sequential Chest X-rays (CXRs) has received limited attention. Monitoring the progression of pathologies that are visualized through chest imaging poses several challenges in anatomical motion estimation and image registration, i.e., spatially aligning the two images and modeling temporal dynamics in change detection. In this work, we propose CheXRelNet, a neural model that can track longitudinal pathology change relations between two CXRs. CheXRelNet incorporates local and global visual features, utilizes inter-image and intra-image anatomical information, and learns dependencies between anatomical region attributes, to accurately predict disease change for a pair of CXRs. Experimental results on the Chest ImaGenome dataset show increased downstream performance compared to baselines. Code is available at https://github.com/PLAN-Lab/ChexRelNet

arXiv:2208.00034

MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI

Recovering the 3D motion of the heart from cine cardiac magnetic resonance (CMR) imaging enables the assessment of regional myocardial function and is important for understanding and analyzing cardiovascular disease. However, 3D cardiac motion estimation is challenging because the acquired cine CMR images are usually 2D slices which limit the accurate estimation of through-plane motion. To address this problem, we propose a novel multi-view motion estimation network (MulViMotion), which integrates 2D cine CMR images acquired in short-axis and long-axis planes to learn a consistent 3D motion field of the heart. In the proposed method, a hybrid 2D/3D network is built to generate dense 3D motion fields by learning fused representations from multi-view images. To ensure that the motion estimation is consistent in 3D, a shape regularization module is introduced during training, where shape information from multi-view images is exploited to provide weak supervision to 3D motion estimation. We extensively evaluate the proposed method on 2D cine CMR images from 580 subjects of the UK Biobank study for 3D motion tracking of the left ventricular myocardium. Experimental results show that the proposed method quantitatively and qualitatively outperforms competing methods.

arXiv:2207.12537공식 코드 · Papers with Code

Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation

3D Human body pose and shape estimation within a temporal sequence can be quite critical for understanding human behavior. Despite the significant progress in human pose estimation in the recent years, which are often based on single images or videos, human motion estimation on live stream videos is still a rarely-touched area considering its special requirements for real-time output and temporal consistency. To address this problem, we present a temporally embedded 3D human body pose and shape estimation (TePose) method to improve the accuracy and temporal consistency of pose estimation in live stream videos. TePose uses previous predictions as a bridge to feedback the error for better estimation in the current frame and to learn the correspondence between data frames and predictions in the history. A multi-scale spatio-temporal graph convolutional network is presented as the motion discriminator for adversarial training using datasets without any 3D labeling. We propose a sequential data loading strategy to meet the special start-to-end data processing requirement of live stream. We demonstrate the importance of each proposed module with extensive experiments. The results show the effectiveness of TePose on widely-used human pose benchmarks with state-of-the-art performance.

arXiv:2207.12305

Error-Aware Spatial Ensembles for Video Frame Interpolation

Video frame interpolation~(VFI) algorithms have improved considerably in recent years due to unprecedented progress in both data-driven algorithms and their implementations. Recent research has introduced advanced motion estimation or novel warping methods as the means to address challenging VFI scenarios. However, none of the published VFI works considers the spatially non-uniform characteristics of the interpolation error (IE). This work introduces such a solution. By closely examining the correlation between optical flow and IE, the paper proposes novel error prediction metrics that partition the middle frame into distinct regions corresponding to different IE levels. Building upon this IE-driven segmentation, and through the use of novel error-controlled loss functions, it introduces an ensemble of spatially adaptive interpolation units that progressively processes and integrates the segmented regions. This spatial ensemble results in an effective and computationally attractive VFI solution. Extensive experimentation on popular video interpolation benchmarks indicates that the proposed solution outperforms the current state-of-the-art (SOTA) in applications of current interest.

arXiv:2207.10607

Deep Statistic Shape Model for Myocardium Segmentation

Accurate segmentation and motion estimation of myocardium have always been important in clinic field, which essentially contribute to the downstream diagnosis. However, existing methods cannot always guarantee the shape integrity for myocardium segmentation. In addition, motion estimation requires point correspondence on the myocardium region across different frames. In this paper, we propose a novel end-to-end deep statistic shape model to focus on myocardium segmentation with both shape integrity and boundary correspondence preserving. Specifically, myocardium shapes are represented by a fixed number of points, whose variations are extracted by Principal Component Analysis (PCA). Deep neural network is used to predict the transformation parameters (both affine and deformation), which are then used to warp the mean point cloud to the image domain. Furthermore, a differentiable rendering layer is introduced to incorporate mask supervision into the framework to learn more accurate point clouds. In this way, the proposed method is able to consistently produce anatomically reasonable segmentation mask without post processing. Additionally, the predicted point cloud guarantees boundary correspondence for sequential images, which contributes to the downstream tasks, such as the motion estimation of myocardium. We conduct several experiments to demonstrate the effectiveness of the proposed method on several benchmark datasets.

arXiv:2207.07469

USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks

In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic information for improved regularization of depth and optical flow maps, multimodal fusion and occlusion filling considering dynamic rigid object motions as independent SE(3) transformations. Furthermore, complementary to pure photo-metric matching, we propose matching of semantic features, pixel-wise classes and object instance borders between the consecutive images. In contrast to previous methods, we propose a network architecture that jointly predicts all outputs using shared encoders and allows passing information across the task-domains, e.g., the prediction of optical flow can benefit from the prediction of the depth. Furthermore, we explicitly learn the depth and optical flow occlusion maps inside the network, which are leveraged in order to improve the predictions in therespective regions. We present results on the popular KITTI dataset and show that our approach outperforms other methods by a large margin.

arXiv:2207.05588공식 코드 · Papers with Code

Ego-motion Estimation Based on Fusion of Images and Events

Event camera is a novel bio-inspired vision sensor that outputs event stream. In this paper, we propose a novel data fusion algorithm called EAS to fuse conventional intensity images with the event stream. The fusion result is applied to some ego-motion estimation frameworks, and is evaluated on a public dataset acquired in dim scenes. In our 3-DoF rotation estimation framework, EAS achieves the highest estimation accuracy among intensity images and representations of events including event slice, TS and SITS. Compared with original images, EAS reduces the average APE by 69%, benefiting from the inclusion of more features for tracking. The result shows that our algorithm effectively leverages the high dynamic range of event cameras to improve the performance of the ego-motion estimation framework based on optical flow tracking in difficult illumination conditions.

arXiv:2207.04680공식 코드 · Papers with Code

Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics

Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years. Although current methods have reached a high up-to-scale accuracy, they usually fail to learn the true scale metric due to the inherent scale ambiguity from training with monocular sequences. In this work, we tackle this problem and propose DynaDepth, a novel scale-aware framework that integrates information from vision and IMU motion dynamics. Specifically, we first propose an IMU photometric loss and a cross-sensor photometric consistency loss to provide dense supervision and absolute scales. To fully exploit the complementary information from both sensors, we further drive a differentiable camera-centric extended Kalman filter (EKF) to update the IMU preintegrated motions when observing visual measurements. In addition, the EKF formulation enables learning an ego-motion uncertainty measure, which is non-trivial for unsupervised methods. By leveraging IMU during training, DynaDepth not only learns an absolute scale, but also provides a better generalization ability and robustness against vision degradation such as illumination change and moving objects. We validate the effectiveness of DynaDepth by conducting extensive experiments and simulations on the KITTI and Make3D datasets.

arXiv:2207.00909

Drift Reduction for Monocular Visual Odometry of Intelligent Vehicles using Feedforward Neural Networks

In this paper, an approach for reducing the drift in monocular visual odometry algorithms is proposed based on a feedforward neural network. A visual odometry algorithm computes the incremental motion of the vehicle between the successive camera frames, then integrates these increments to determine the pose of the vehicle. The proposed neural network reduces the errors in the pose estimation of the vehicle which results from the inaccuracies in features detection and matching, camera intrinsic parameters, and so on. These inaccuracies are propagated to the motion estimation of the vehicle causing larger amounts of estimation errors. The drift reducing neural network identifies such errors based on the motion of features in the successive camera frames leading to more accurate incremental motion estimates. The proposed drift reducing neural network is trained and validated using the KITTI dataset and the results show the efficacy of the proposed approach in reducing the errors in the incremental orientation estimation, thus reducing the overall error in the pose estimation.

arXiv:2206.13850

When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation

Self-supervised deep learning methods for joint depth and ego-motion estimation can yield accurate trajectories without needing ground-truth training data. However, as they typically use photometric losses, their performance can degrade significantly when the assumptions these losses make (e.g. temporal illumination consistency, a static scene, and the absence of noise and occlusions) are violated. This limits their use for e.g. nighttime sequences, which tend to contain many point light sources (including on dynamic objects) and low signal-to-noise ratio (SNR) in darker image regions. In this paper, we show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images. First, we introduce a per-pixel neural intensity transformation to compensate for the light changes that occur between successive frames. Second, we predict a per-pixel residual flow map that we use to correct the reprojection correspondences induced by the estimated ego-motion and depth from the networks. And third, we denoise the training images to improve the robustness and accuracy of our approach. These changes allow us to train a single model for both day and nighttime images without needing separate encoders or extra feature networks like existing methods. We perform extensive experiments and ablation studies on the challenging Oxford RobotCar dataset to demonstrate the efficacy of our approach for both day and nighttime sequences.

arXiv:2206.13613공식 코드 · Papers with Code

Flexible-Rate Learned Hierarchical Bi-Directional Video Compression With Motion Refinement and Frame-Level Bit Allocation

This paper presents improvements and novel additions to our recent work on end-to-end optimized hierarchical bi-directional video compression to further advance the state-of-the-art in learned video compression. As an improvement, we combine motion estimation and prediction modules and compress refined residual motion vectors for improved rate-distortion performance. As novel addition, we adapted the gain unit proposed for image compression to flexible-rate video compression in two ways: first, the gain unit enables a single encoder model to operate at multiple rate-distortion operating points; second, we exploit the gain unit to control bit allocation among intra-coded vs. bi-directionally coded frames by fine tuning corresponding models for truly flexible-rate learned video coding. Experimental results demonstrate that we obtain state-of-the-art rate-distortion performance exceeding those of all prior art in learned video coding.

arXiv:2206.13076

SearchMorph:Multi-scale Correlation Iterative Network for Deformable Registration

Deformable image registration can obtain dynamic information about images, which is of great significance in medical image analysis. The unsupervised deep learning registration method can quickly achieve high registration accuracy without labels. However, these methods generally suffer from uncorrelated features, poor ability to register large deformations and details, and unnatural deformation fields. To address the issues above, we propose an unsupervised multi-scale correlation iterative registration network (SearchMorph). In the proposed network, we introduce a correlation layer to strengthen the relevance between features and construct a correlation pyramid to provide multi-scale relevance information for the network. We also design a deformation field iterator, which improves the ability of the model to register details and large deformations through the search module and GRU while ensuring that the deformation field is realistic. We use single-temporal brain MR images and multi-temporal echocardiographic sequences to evaluate the model's ability to register large deformations and details. The experimental results demonstrate that the method in this paper achieves the highest registration accuracy and the lowest folding point ratio using a short elapsed time to state-of-the-art.

arXiv:2206.12946

AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation

Motion estimation approaches typically employ sensor fusion techniques, such as the Kalman Filter, to handle individual sensor failures. More recently, deep learning-based fusion approaches have been proposed, increasing the performance and requiring less model-specific implementations. However, current deep fusion approaches often assume that sensors are synchronised, which is not always practical, especially for low-cost hardware. To address this limitation, in this work, we propose AFT-VO, a novel transformer-based sensor fusion architecture to estimate VO from multiple sensors. Our framework combines predictions from asynchronous multi-view cameras and accounts for the time discrepancies of measurements coming from different sources. Our approach first employs a Mixture Density Network (MDN) to estimate the probability distributions of the 6-DoF poses for every camera in the system. Then a novel transformer-based fusion module, AFT-VO, is introduced, which combines these asynchronous pose estimations, along with their confidences. More specifically, we introduce Discretiser and Source Encoding techniques which enable the fusion of multi-source asynchronous signals. We evaluate our approach on the popular nuScenes and KITTI datasets. Our experiments demonstrate that multi-view fusion for VO estimation provides robust and accurate trajectories, outperforming the state of the art in both challenging weather and lighting conditions.

arXiv:2206.12464

Motion Estimation for Large Displacements and Deformations

Large displacement optical flow is an integral part of many computer vision tasks. Variational optical flow techniques based on a coarse-to-fine scheme interpolate sparse matches and locally optimize an energy model conditioned on colour, gradient and smoothness, making them sensitive to noise in the sparse matches, deformations, and arbitrarily large displacements. This paper addresses this problem and presents HybridFlow, a variational motion estimation framework for large displacements and deformations. A multi-scale hybrid matching approach is performed on the image pairs. Coarse-scale clusters formed by classifying pixels according to their feature descriptors are matched using the clusters' context descriptors. We apply a multi-scale graph matching on the finer-scale superpixels contained within each matched pair of coarse-scale clusters. Small clusters that cannot be further subdivided are matched using localized feature matching. Together, these initial matches form the flow, which is propagated by an edge-preserving interpolation and variational refinement. Our approach does not require training and is robust to substantial displacements and rigid and non-rigid transformations due to motion in the scene, making it ideal for large-scale imagery such as Wide-Area Motion Imagery (WAMI). More notably, HybridFlow works on directed graphs of arbitrary topology representing perceptual groups, which improves motion estimation in the presence of significant deformations. We demonstrate HybridFlow's superior performance to state-of-the-art variational techniques on two benchmark datasets and report comparable results with state-of-the-art deep-learning-based techniques.

arXiv:2206.10480공식 코드 · Papers with Code

Learning to Estimate and Refine Fluid Motion with Physical Dynamics

Extracting information on fluid motion directly from images is challenging. Fluid flow represents a complex dynamic system governed by the Navier-Stokes equations. General optical flow methods are typically designed for rigid body motion, and thus struggle if applied to fluid motion estimation directly. Further, optical flow methods only focus on two consecutive frames without utilising historical temporal information, while the fluid motion (velocity field) can be considered a continuous trajectory constrained by time-dependent partial differential equations (PDEs). This discrepancy has the potential to induce physically inconsistent estimations. Here we propose an unsupervised learning based prediction-correction scheme for fluid flow estimation. An estimate is first given by a PDE-constrained optical flow predictor, which is then refined by a physical based corrector. The proposed approach outperforms optical flow methods and shows competitive results compared to existing supervised learning based methods on a benchmark dataset. Furthermore, the proposed approach can generalize to complex real-world fluid scenarios where ground truth information is effectively unknowable. Finally, experiments demonstrate that the physical corrector can refine flow estimates by mimicking the operator splitting method commonly utilised in fluid dynamical simulation.

arXiv:2206.08572공식 코드 · Papers with Code

Enhanced Bi-directional Motion Estimation for Video Frame Interpolation

We present a novel simple yet effective algorithm for motion-based video frame interpolation. Existing motion-based interpolation methods typically rely on a pre-trained optical flow model or a U-Net based pyramid network for motion estimation, which either suffer from large model size or limited capacity in handling complex and large motion cases. In this work, by carefully integrating intermediateoriented forward-warping, lightweight feature encoder, and correlation volume into a pyramid recurrent framework, we derive a compact model to simultaneously estimate the bidirectional motion between input frames. It is 15 times smaller in size than PWC-Net, yet enables more reliable and flexible handling of challenging motion cases. Based on estimated bi-directional motion, we forward-warp input frames and their context features to intermediate frame, and employ a synthesis network to estimate the intermediate frame from warped representations. Our method achieves excellent performance on a broad range of video frame interpolation benchmarks. Code and trained models are available at \url{https://github.com/srcn-ivl/EBME}.