PyTorchKR Papers

최신 논문

총 179편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2104.03437공식 코드 · Papers with Code

CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

In this work, we tackle the problem of category-level online pose tracking of objects from point cloud sequences. For the first time, we propose a unified framework that can handle 9DoF pose tracking for novel rigid object instances as well as per-part pose tracking for articulated objects from known categories. Here the 9DoF pose, comprising 6D pose and 3D size, is equivalent to a 3D amodal bounding box representation with free 6D pose. Given the depth point cloud at the current frame and the estimated pose from the last frame, our novel end-to-end pipeline learns to accurately update the pose. Our pipeline is composed of three modules: 1) a pose canonicalization module that normalizes the pose of the input depth point cloud; 2) RotationNet, a module that directly regresses small interframe delta rotations; and 3) CoordinateNet, a module that predicts the normalized coordinates and segmentation, enabling analytical computation of the 3D size and translation. Leveraging the small pose regime in the pose-canonicalized point clouds, our method integrates the best of both worlds by combining dense coordinate prediction and direct rotation regression, thus yielding an end-to-end differentiable pipeline optimized for 9DoF pose accuracy (without using non-differentiable RANSAC). Our extensive experiments demonstrate that our method achieves new state-of-the-art performance on category-level rigid object pose (NOCS-REAL275) and articulated object pose benchmarks (SAPIEN, BMVC) at the fastest FPS ~12.

arXiv:2101.09745공식 코드 · Papers with Code

Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views

In this work we propose an approach for estimating 3D human poses of multiple people from a set of calibrated cameras. Estimating 3D human poses from multiple views has several compelling properties: human poses are estimated within a global coordinate space and multiple cameras provide an extended field of view which helps in resolving ambiguities, occlusions and motion blur. Our approach builds upon a real-time 2D multi-person pose estimation system and greedily solves the association problem between multiple views. We utilize bipartite matching to track multiple people over multiple frames. This proofs to be especially efficient as problems associated with greedy matching such as occlusion can be easily resolved in 3D. Our approach achieves state-of-the-art results on popular benchmarks and may serve as a baseline for future work.

arXiv:2101.04281공식 코드 · Papers with Code

Temporally Guided Articulated Hand Pose Tracking in Surgical Videos

Articulated hand pose tracking is an under-explored problem that carries the potential for use in an extensive number of applications, especially in the medical domain. With a robust and accurate tracking system on in-vivo surgical videos, the motion dynamics and movement patterns of the hands can be captured and analyzed for many rich tasks. In this work, we propose a novel hand pose estimation model, Res152-CondPose, which improves detection and tracking accuracy by incorporating a hand pose prior into its pose prediction. We show improvements over state-of-the-art methods which provide frame-wise independent predictions, by following a temporally guided approach that effectively leverages past predictions. Additionally, we collect the first dataset, Surgical Hands, that provides multi-instance articulated hand pose annotations for in-vivo videos. Our dataset contains 76 video clips from 28 publicly available surgical videos and over 8.1k annotated hand pose instances. We provide bounding boxes, articulated hand pose annotations, and tracking IDs to enable multi-instance area-based and articulated tracking. When evaluated on Surgical Hands, we show our method outperforms the state-of-the-art method using mean Average Precision (mAP), to measure pose estimation accuracy, and Multiple Object Tracking Accuracy (MOTA), to assess pose tracking performance. Both the code and dataset are available at https://github.com/MichiganCOG/Surgical_ Hands_RELEASE.

arXiv:1802.04388

Statistical Sensor Fusion of a 9-DoF MEMS IMU for Indoor Navigation

Sensor fusion of a MEMS IMU with a magnetometer is a popular system design, because such 9-DoF (degrees of freedom) systems are capable of achieving drift-free 3D orientation tracking. However, these systems are often vulnerable to ambient magnetic distortions and lack useful position information; in the absence of external position aiding (e.g. satellite/ultra-wideband positioning systems) the dead-reckoned position accuracy from a 9-DoF MEMS IMU deteriorates rapidly due to unmodelled errors. Positioning information is valuable in many satellite-denied geomatics applications (e.g. indoor navigation, location-based services, etc.). This paper proposes an improved 9-DoF IMU indoor pose tracking method using batch optimization. By adopting a robust in-situ user self-calibration approach to model the systematic errors of the accelerometer, gyroscope, and magnetometer simultaneously in a tightly-coupled post-processed least-squares framework, the accuracy of the estimated trajectory from a 9-DoF MEMS IMU can be improved. Through a combination of relative magnetic measurement updates and a robust weight function, the method is able to tolerate a high level of magnetic distortions. The proposed auto-calibration method was tested in-use under various heterogeneous magnetic field conditions to mimic a person walking with the sensor in their pocket, a person checking their phone, and a person walking with a smartwatch. In these experiments, the presented algorithm improved the in-situ dead-reckoning orientation accuracy by 79.8 - 89.5% and the dead-reckoned positioning accuracy by 72.9 - 92.8%, thus reducing the relative positioning error from metre-level to decimetre-level after ten seconds of integration, without making assumptions about the user's dynamics.

arXiv:2011.06243

PoseTrackReID: Dataset Description

Current datasets for video-based person re-identification (re-ID) do not include structural knowledge in form of human pose annotations for the persons of interest. Nonetheless, pose information is very helpful to disentangle useful feature information from background or occlusion noise. Especially real-world scenarios, such as surveillance, contain a lot of occlusions in human crowds or by obstacles. On the other hand, video-based person re-ID can benefit other tasks such as multi-person pose tracking in terms of robust feature matching. For that reason, we present PoseTrackReID, a large-scale dataset for multi-person pose tracking and video-based person re-ID. With PoseTrackReID, we want to bridge the gap between person re-ID and multi-person pose tracking. Additionally, this dataset provides a good benchmark for current state-of-the-art methods on multi-frame person re-ID.

arXiv:2010.10007

A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

This paper presents our solution to ACM MM challenge: Large-scale Human-centric Video Analysis in Complex Events\cite{lin2020human}; specifically, here we focus on Track3: Crowd Pose Tracking in Complex Events. Remarkable progress has been made in multi-pose training in recent years. However, how to track the human pose in crowded and complex environments has not been well addressed. We formulate the problem as several subproblems to be solved. First, we use a multi-object tracking method to assign human ID to each bounding box generated by the detection model. After that, a pose is generated to each bounding box with ID. At last, optical flow is used to take advantage of the temporal information in the videos and generate the final pose tracking result.

arXiv:2008.05079공식 코드 · Papers with Code

BiHand: Recovering Hand Mesh with Multi-stage Bisected Hourglass Networks

3D hand estimation has been a long-standing research topic in computer vision. A recent trend aims not only to estimate the 3D hand joint locations but also to recover the mesh model. However, achieving those goals from a single RGB image remains challenging. In this paper, we introduce an end-to-end learnable model, BiHand, which consists of three cascaded stages, namely 2D seeding stage, 3D lifting stage, and mesh generation stage. At the output of BiHand, the full hand mesh will be recovered using the joint rotations and shape parameters predicted from the network. Inside each stage, BiHand adopts a novel bisecting design which allows the networks to encapsulate two closely related information (e.g. 2D keypoints and silhouette in 2D seeding stage, 3D joints, and depth map in 3D lifting stage, joint rotations and shape parameters in the mesh generation stage) in a single forward pass. As the information represents different geometry or structure details, bisecting the data flow can facilitate optimization and increase robustness. For quantitative evaluation, we conduct experiments on two public benchmarks, namely the Rendered Hand Dataset (RHD) and the Stereo Hand Pose Tracking Benchmark (STB). Extensive experiments show that our model can achieve superior accuracy in comparison with state-of-the-art methods, and can produce appealing 3D hand meshes in several severe conditions.

arXiv:2007.13866공식 코드 · Papers with Code

se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome and difficult to collect for 6D poses, which complicates machine learning solutions, and (iii) incremental error drift often accumulates in long term tracking to necessitate re-initialization of the object's pose. This work proposes a data-driven optimization approach for long-term, 6D pose tracking. It aims to identify the optimal relative pose given the current RGB-D observation and a synthetic image conditioned on the previous best estimate and the object's model. The key contribution in this context is a novel neural network architecture, which appropriately disentangles the feature encoding to help reduce domain shift, and an effective 3D orientation representation via Lie Algebra. Consequently, even when the network is trained only with synthetic data can work effectively over real images. Comprehensive experiments over benchmarks - existing ones as well as a new dataset with significant occlusions related to object manipulation - show that the proposed approach achieves consistently robust estimates and outperforms alternatives, even though they have been trained with real images. The approach is also the most computationally efficient among the alternatives and achieves a tracking frequency of 90.9Hz.

arXiv:2006.10204공식 코드 · Papers with Code

BlazePose: On-device Real-time Body Pose tracking

We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates.

arXiv:2006.01668

Variational Inference and Learning of Piecewise-linear Dynamical Systems

Modeling the temporal behavior of data is of primordial importance in many scientific and engineering fields. Baseline methods assume that both the dynamic and observation equations follow linear-Gaussian models. However, there are many real-world processes that cannot be characterized by a single linear behavior. Alternatively, it is possible to consider a piecewise-linear model which, combined with a switching mechanism, is well suited when several modes of behavior are needed. Nevertheless, switching dynamical systems are intractable because of their computational complexity increases exponentially with time. In this paper, we propose a variational approximation of piecewise linear dynamical systems. We provide full details of the derivation of two variational expectation-maximization algorithms, a filter and a smoother. We show that the model parameters can be split into two sets, static and dynamic parameters, and that the former parameters can be estimated off-line together with the number of linear modes, or the number of states of the switching variable. We apply the proposed method to a visual tracking problem, namely head-pose tracking, and we thoroughly compare our algorithm with several state of the art trackers.

arXiv:2004.12652

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

Video annotation is expensive and time consuming. Consequently, datasets for multi-person pose estimation and tracking are less diverse and have more sparse annotations compared to large scale image datasets for human pose estimation. This makes it challenging to learn deep learning based models for associating keypoints across frames that are robust to nuisance factors such as motion blur and occlusions for the task of multi-person pose tracking. To address this issue, we propose an approach that relies on keypoint correspondences for associating persons in videos. Instead of training the network for estimating keypoint correspondences on video data, it is trained on a large scale image datasets for human pose estimation using self-supervision. Combined with a top-down framework for human pose estimation, we use keypoints correspondences to (i) recover missed pose detections (ii) associate pose detections across video frames. Our approach achieves state-of-the-art results for multi-frame pose estimation and multi-person pose tracking on the PosTrack $2017$ and PoseTrack $2018$ data sets.

arXiv:2004.10335공식 코드 · Papers with Code

How to track your dragon: A Multi-Attentional Framework for real-time RGB-D 6-DOF Object Pose Tracking

We present a novel multi-attentional convolutional architecture to tackle the problem of real-time RGB-D 6D object pose tracking of single, known objects. Such a problem poses multiple challenges originating both from the objects' nature and their interaction with their environment, which previous approaches have failed to fully address. The proposed framework encapsulates methods for background clutter and occlusion handling by integrating multiple parallel soft spatial attention modules into a multitask Convolutional Neural Network (CNN) architecture. Moreover, we consider the special geometrical properties of both the object's 3D model and the pose space, and we use a more sophisticated approach for data augmentation during training. The provided experimental results confirm the effectiveness of the proposed multi-attentional architecture, as it improves the State-of-the-Art (SoA) tracking performance by an average score of 34.03% for translation and 40.01% for rotation, when tested on the most complete dataset designed, up to date,for the problem of RGB-D object tracking.

arXiv:2004.00740공식 코드 · Papers with Code

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO\&VIO) techniques are well-developed for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems, we propose an efficient monocular camera localization method in prior LiDAR maps using direct 2D-3D line correspondences. To handle the appearance differences and modality gaps between LiDAR point clouds and images, geometric 3D lines are extracted offline from LiDAR maps while robust 2D lines are extracted online from video sequences. With the pose prediction from VIO, we can efficiently obtain coarse 2D-3D line correspondences. Then the camera poses and 2D-3D correspondences are iteratively optimized by minimizing the projection error of correspondences and rejecting outliers. Experimental results on the EurocMav dataset and our collected dataset demonstrate that the proposed method can efficiently estimate camera poses without accumulated drifts or pose jumps in structured environments.

arXiv:2003.13743

Combining detection and tracking for human pose estimation in videos

We propose a novel top-down approach that tackles the problem of multi-person human pose estimation and tracking in videos. In contrast to existing top-down approaches, our method is not limited by the performance of its person detector and can predict the poses of person instances not localized. It achieves this capability by propagating known person locations forward and backward in time and searching for poses in those regions. Our approach consists of three components: (i) a Clip Tracking Network that performs body joint detection and tracking simultaneously on small video clips; (ii) a Video Tracking Pipeline that merges the fixed-length tracklets produced by the Clip Tracking Network to arbitrary length tracks; and (iii) a Spatial-Temporal Merging procedure that refines the joint locations based on spatial and temporal smoothing terms. Thanks to the precision of our Clip Tracking Network and our merging procedure, our approach produces very accurate joint predictions and can fix common mistakes on hard scenarios like heavily entangled people. Our approach achieves state-of-the-art results on both joint detection and tracking, on both the PoseTrack 2017 and 2018 datasets, and against all top-down and bottom-down approaches.

arXiv:2002.02792

AnimePose: Multi-person 3D pose estimation and animation

3D animation of humans in action is quite challenging as it involves using a huge setup with several motion trackers all over the person's body to track the movements of every limb. This is time-consuming and may cause the person discomfort in wearing exoskeleton body suits with motion sensors. In this work, we present a trivial yet effective solution to generate 3D animation of multiple persons from a 2D video using deep learning. Although significant improvement has been achieved recently in 3D human pose estimation, most of the prior works work well in case of single person pose estimation and multi-person pose estimation is still a challenging problem. In this work, we firstly propose a supervised multi-person 3D pose estimation and animation framework namely AnimePose for a given input RGB video sequence. The pipeline of the proposed system consists of various modules: i) Person detection and segmentation, ii) Depth Map estimation, iii) Lifting 2D to 3D information for person localization iv) Person trajectory prediction and human pose tracking. Our proposed system produces comparable results on previous state-of-the-art 3D multi-person pose estimation methods on publicly available datasets MuCo-3DHP and MuPoTS-3D datasets and it also outperforms previous state-of-the-art human pose tracking methods by a significant margin of 11.7% performance gain on MOTA score on Posetrack 2018 dataset.

arXiv:2001.06875

RGB-D Odometry and SLAM

The emergence of modern RGB-D sensors had a significant impact in many application fields, including robotics, augmented reality (AR) and 3D scanning. They are low-cost, low-power and low-size alternatives to traditional range sensors such as LiDAR. Moreover, unlike RGB cameras, RGB-D sensors provide the additional depth information that removes the need of frame-by-frame triangulation for 3D scene reconstruction. These merits have made them very popular in mobile robotics and AR, where it is of great interest to estimate ego-motion and 3D scene structure. Such spatial understanding can enable robots to navigate autonomously without collisions and allow users to insert virtual entities consistent with the image stream. In this chapter, we review common formulations of odometry and Simultaneous Localization and Mapping (known by its acronym SLAM) using RGB-D stream input. The two topics are closely related, as the former aims to track the incremental camera motion with respect to a local map of the scene, and the latter to jointly estimate the camera trajectory and the global map with consistency. In both cases, the standard approaches minimize a cost function using nonlinear optimization techniques. This chapter consists of three main parts: In the first part, we introduce the basic concept of odometry and SLAM and motivate the use of RGB-D sensors. We also give mathematical preliminaries relevant to most odometry and SLAM algorithms. In the second part, we detail the three main components of SLAM systems: camera pose tracking, scene mapping and loop closing. For each component, we describe different approaches proposed in the literature. In the final part, we provide a brief discussion on advanced research topics with the references to the state-of-the-art.

arXiv:1912.02323

15 Keypoints Is All You Need

Pose tracking is an important problem that requires identifying unique human pose-instances and matching them temporally across different frames of a video. However, existing pose tracking methods are unable to accurately model temporal relationships and require significant computation, often computing the tracks offline. We present an efficient Multi-person Pose Tracking method, KeyTrack, that only relies on keypoint information without using any RGB or optical flow information to track human keypoints in real-time. Keypoints are tracked using our Pose Entailment method, in which, first, a pair of pose estimates is sampled from different frames in a video and tokenized. Then, a Transformer-based network makes a binary classification as to whether one pose temporally follows another. Furthermore, we improve our top-down pose estimation method with a novel, parameter-free, keypoint refinement technique that improves the keypoint estimates used during the Pose Entailment step. We achieve state-of-the-art results on the PoseTrack'17 and the PoseTrack'18 benchmarks while using only a fraction of the computation required by most other methods for computing the tracking information.

arXiv:1910.10750공식 코드 · Papers with Code

6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints

We present 6-PACK, a deep learning approach to category-level 6D object pose tracking on RGB-D data. Our method tracks in real-time novel object instances of known object categories such as bowls, laptops, and mugs. 6-PACK learns to compactly represent an object by a handful of 3D keypoints, based on which the interframe motion of an object instance can be estimated through keypoint matching. These keypoints are learned end-to-end without manual supervision in order to be most effective for tracking. Our experiments show that our method substantially outperforms existing methods on the NOCS category-level 6D pose estimation benchmark and supports a physical robot to perform simple vision-based closed-loop manipulation tasks. Our code and video are available at https://sites.google.com/view/6packtracking.

arXiv:1910.06007

Multi-view consensus CNN for 3D facial landmark placement

The rapid increase in the availability of accurate 3D scanning devices has moved facial recognition and analysis into the 3D domain. 3D facial landmarks are often used as a simple measure of anatomy and it is crucial to have accurate algorithms for automatic landmark placement. The current state-of-the-art approaches have yet to gain from the dramatic increase in performance reported in human pose tracking and 2D facial landmark placement due to the use of deep convolutional neural networks (CNN). Development of deep learning approaches for 3D meshes has given rise to the new subfield called geometric deep learning, where one topic is the adaptation of meshes for the use of deep CNNs. In this work, we demonstrate how methods derived from geometric deep learning, namely multi-view CNNs, can be combined with recent advances in human pose tracking. The method finds 2D landmark estimates and propagates this information to 3D space, where a consensus method determines the accurate 3D face landmark position. We utilise the method on a standard 3D face dataset and show that it outperforms current methods by a large margin. Further, we demonstrate how models trained on 3D range scans can be used to accurately place anatomical landmarks in magnetic resonance images.

arXiv:1909.07031

Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor

It is an effective strategy for the multi-person pose tracking task in videos to employ prediction and pose matching in a frame-by-frame manner. For this type of approach, uncertainty-aware modeling is essential because precise prediction is impossible. However, previous studies have relied on only a single prediction without incorporating uncertainty, which can cause critical tracking errors if the prediction is unreliable. This paper proposes an extension to this approach with Sequential Monte Carlo (SMC). This naturally reformulates the tracking scheme to handle multiple predictions (or hypotheses) of poses, thereby mitigating the negative effect of prediction errors. An important component of SMC, i.e., a proposal distribution, is designed as a probabilistic neural pose predictor, which can propose diverse and plausible hypotheses by incorporating epistemic uncertainty and heteroscedastic aleatoric uncertainty. In addition, a recurrent architecture is introduced to our neural modeling to utilize time-sequence information of poses to manage difficult situations, such as the frequent disappearance and reappearances of poses. Compared to existing baselines, the proposed method achieves a state-of-the-art MOTA score on the PoseTrack2018 validation dataset by reducing approximately 50% of tracking errors from a state-of-the art baseline method.