The Five Points Pose Problem : A New and Accurate Solution Adapted to any Geometric Configuration
Institut Recherche Communications Cybernétique de Nantes (IRCCyN)（南特通信与控制研究所（IRCCyN））；Institut de Recherche sur les Sciences et Techniques de la Ville（城市科学与技术研究所）；DDE - Seine Maritime（塞纳滨海省设备局）
Mahzad Kalantari, Franck Jung, JeanPierre Guedon, Nicolas Paparoditis
The goal of this paper is to estimate directly the rotation and translation between two stereoscopic images with the help of five homologous points. The methodology presented does not mix the rotation and translation parameters, which is comparably an important advantage over the methods using the well-known essential matrix. This results in correct behavior and accuracy for situations otherwise known as quite unfavorable, such as planar scenes, or panoramic sets of images (with a null base length), while providing quite comparable results for more "standard" cases. The resolution of the algebraic polynomials resulting from the modeling of the coplanarity constraint is made with the help of powerful algebraic solver tools (the Groebner bases and the Rational Univariate Representation).
The ultimate goal for an inference model is to be robust and functional in real life applications. However, training vs. test data domain gaps often negatively affect model performance. This issue is especially critical for the monocular 3D human pose estimation problem, in which 3D human data is often collected in a controlled lab setting. In this paper, we focus on alleviating the negative effect of domain shift in both appearance and pose space for 3D human pose estimation by presenting our adapted human pose (AHuP) approach. AHuP is built upon two key components: (1) semantically aware ada…
We give a new algorithmic solution to the well-known five-point relative pose problem. Our approach does not deal with the famous cubic constraint on an essential matrix. Instead, we use the Cayley representation of rotations in order to obtain a polynomial system from epipolar constraints. Solving that system, we directly get relative rotation and translation parameters of the cameras in terms of roots of a 10th degree polynomial.
FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学类脑智能科学与技术研究院）；Department of Automation, Tsinghua University（清华大学自动化系）；Chair for Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich（慕尼黑工业大学计算机辅助医疗程序与增强现实讲座）
Blind image deblurring (BID) is an ill-posed inverse problem, usually addressed by imposing prior knowledge on the (unknown) image and on the blurring filter. Most of the work on BID has focused on natural images, using image priors based on statistical properties of generic natural images. However, in many applications, it is known that the image being recovered belongs to some specific class (e.g., text, face, fingerprints), and exploiting this knowledge allows obtaining more accurate priors. In this work, we propose a method where a Gaussian mixture model (GMM) is used to learn a class-adap…
In this paper, we propose a novel approach to solve the pose guided person image generation task. We assume that the relation between pose and appearance information can be described by a simple matrix operation in hidden space. Based on this assumption, our method estimates a pose-invariant feature matrix for each identity, and uses it to predict the target appearance conditioned on the target pose. The estimation process is formulated as a p-norm regression problem in hidden space. By utilizing the differentiation of the solution of this regression problem, the parameters of the whole framew…
This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this problem by improving the diversity of the training data. We argue that diversity alone is not sufficient and that the characteristics of the training data need to be adapted to those of the new dataset such as camera viewpoint, position, human actions, and body size. To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human …
Institut für Photogrammetrie und Fernerkundung, Universität Karlsruhe (TH)（卡尔斯鲁厄理工学院摄影测量与遥感研究所）
A hierarchical interval subdivision is shown to lead to a $p$-adic encoding of image data. This allows in the case of the relative pose problem in computer vision and photogrammetry to derive equations having 2-adic numbers as coefficients, and to use Hensel's lifting method to their solution. This method is applied to the linear and non-linear equations coming from eight, seven or five point correspondences. An inherent property of the method is its robustness.
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人社会研究院）；University of California, Irvine（加利福尼亚大学尔湾分校）
The end-to-end Human Mesh Recovery (HMR) approach has been successfully used for 3D body reconstruction. However, most HMR-based frameworks reconstruct human body by directly learning mesh parameters from images or videos, while lacking explicit guidance of 3D human pose in visual data. As a result, the generated mesh often exhibits incorrect pose for complex activities. To tackle this problem, we propose to exploit 3D pose to calibrate human mesh. Specifically, we develop two novel Pose Calibration frameworks, i.e., Serial PC-HMR and Parallel PC-HMR. By coupling advanced 3D pose estimators an…
This paper addresses the problem of 3D hand pose estimation from a monocular RGB image. While previous methods have shown great success, the structure of hands has not been fully exploited, which is critical in pose estimation. To this end, we propose a regularized graph representation learning under a conditional adversarial learning framework for 3D hand pose estimation, aiming to capture structural inter-dependencies of hand joints. In particular, we estimate an initial hand pose from a parametric hand model as a prior of hand structure, which regularizes the inference of the structural def…
The rolling shutter camera has received great attention due to its low cost imaging capability, however, the estimation of relative pose between rolling shutter cameras still remains a difficult problem owing to its line-by-line image capturing characteristics. To alleviate this problem, we exploit gyroscope measurements, angular velocity, along with image measurement to compute the relative pose between rolling shutter cameras. The gyroscope measurements provide the information about instantaneous motion that causes the rolling shutter distortion. Having gyroscope measurements in one hand, we…
Until recently Intelligence, Surveillance, and Reconnaissance (ISR) focused on acquiring behavioral information of the targets and their activities. Continuous evolution of intelligence being gathered of the human centric activities has put increased focus on the humans, especially inferring their innate characteristics - size, shapes and physiology. These bio-signatures extracted from the surveillance sensors can be used to deduce age, ethnicity, gender and actions, and further characterize human actions in unseen scenarios. However, recovery of pose and shape of humans in such monocular vide…
Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset
Shanghai Center for Brain Science and Brain-Inspired Technology（上海脑科学与类脑研究中心）；NYU-ECNU Institute of Brain and Cognitive Science, New York University Shanghai（上海纽约大学纽约大学-华东师范大学脑与认知科学研究院）
KTH–Royal Institute of Technology（瑞典皇家理工学院）；Elekta AB（医科达公司）；University of Cambridge（剑桥大学）；Western Norway University of Applied Sciences（西挪威应用科学大学）
The paper considers the problem of performing a task defined on a model parameter that is only observed indirectly through noisy data in an ill-posed inverse problem. A key aspect is to formalize the steps of reconstruction and task as appropriate estimators (non-randomized decision rules) in statistical estimation problems. The implementation makes use of (deep) neural networks to provide a differentiable parametrization of the family of estimators for both steps. These networks are combined and jointly trained against suitable supervised training data in order to minimize a joint differentia…
We study the problem of aligning two sets of 3D geometric primitives given known correspondences. Our first contribution is to show that this primitive alignment framework unifies five perception problems including point cloud registration, primitive (mesh) registration, category-level 3D registration, absolution pose estimation (APE), and category-level APE. Our second contribution is to propose DynAMical Pose estimation (DAMP), the first general and practical algorithm to solve primitive alignment problem by simulating rigid body dynamics arising from virtual springs and damping, where the s…
3D hand pose estimation from a single depth image plays an important role in computer vision and human-computer interaction. Although recent hand pose estimation methods using convolution neural network (CNN) have shown notable improvements in accuracy, most of them have a limitation that they rely on a complex network structure without fully exploiting the articulated structure of the hand. A hand, which is an articulated object, is composed of six local parts: the palm and five independent fingers. Each finger consists of sequential-joints that provide constrained motion, referred to as a ki…
