Related papers: Flow Matching for Probabilistic Monocular 3D Human…

3D human articulated pose recovery from monocular image sequences is very challenging due to the diverse appearances, viewpoints, occlusions, and also the human 3D pose is inherently ambiguous from the monocular imagery. It is thus critical…

We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple…

Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem. The two-dimensional nature of the input results in intrinsic ambiguities which make inferring depth particularly difficult.…

Most 2D human pose estimation benchmarks are nearly saturated, with the exception of crowded scenes. We introduce PMPose, a top-down 2D pose estimator that incorporates the probabilistic formulation and the mask-conditioning. PMPose…

We explore 3D human pose estimation from a single RGB image. While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions. Our approach…

Video based fall detection accuracy has been largely improved due to the recent progress on deep convolutional neural networks. However, there still exists some challenges, such as lighting variation, complex background, which degrade the…

We consider the task of estimating 3D human pose and shape from videos. While existing frame-based approaches have made significant progress, these methods are independently applied to each image, thereby often leading to inconsistent…

6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues…

Current approaches in 3D human pose estimation primarily focus on regressing 3D joint locations, often neglecting critical physical constraints such as bone length consistency and body symmetry. This work introduces a recurrent neural…

Depth estimation is usually ill-posed and ambiguous for monocular camera-based 3D multi-person pose estimation. Since LiDAR can capture accurate depth information in long-range scenes, it can benefit both the global localization of…

Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3D human pose estimation (HPE). Here, the task is to predict a 3D point set of human skeletal…

Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains underexplored.…

Human pose and shape estimation from RGB images is a highly sought after alternative to marker-based motion capture, which is laborious, requires expensive equipment, and constrains capture to laboratory environments. Monocular vision-based…

Estimating human pose and shape from monocular images is a long-standing problem in computer vision. Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention. With the same goal of obtaining…

Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately.…

Most recent 6D object pose methods use 2D optical flow to refine their results. However, the general optical flow methods typically do not consider the target's 3D shape information during matching, making them less effective in 6D object…

Human pose estimation (HPE) with convolutional neural networks (CNNs) for indoor monitoring is one of the major challenges in computer vision. In contrast to HPE in perspective views, an indoor monitoring system can consist of an…

In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features obtained from diverse sources to enable more efficient…

We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction (HRI) scenarios. Our method is based…

Anytime 3D human pose forecasting is crucial to synchronous real-world human-machine interaction, where the term ``anytime" corresponds to predicting human pose at any real-valued time step. However, to the best of our knowledge, all the…