相关论文: Neural Human Pose Prior

We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views. The first (baseline) solution is a basic differentiable algebraic…

We propose to combine recent Convolutional Neural Networks (CNN) models with depth imaging to obtain a reliable and fast multi-person pose estimation algorithm applicable to Human Robot Interaction (HRI) scenarios. Our hypothesis is that…

Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones. However, the lack of unified…

A prior represents a set of beliefs or assumptions about a system, aiding inference and decision-making. In this paper, we introduce the challenge of unsupervised categorical prior learning in pose estimation, where AI models learn a…

3D human reconstruction and animation are long-standing topics in computer graphics and vision. However, existing methods typically rely on sophisticated dense-view capture and/or time-consuming per-subject optimization procedures. To…

Accurate 6D object pose estimation is a fundamental capability for embodied agents, yet remains highly challenging in open-world environments. Many existing methods often rely on closed-set assumptions or geometry-agnostic regression…

We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent complexity of articulated human poses and the scarcity of…

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning,…

Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people. However, cameras generally capture human poses in 2D as images and videos, which can have significant appearance variations across…

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…

Accurate 6-DoF object pose estimation and tracking are critical for reliable robotic manipulation. However, zero-shot methods often fail under viewpoint-induced ambiguities and fixed-camera setups struggle when objects move or become…

An accurate and uncertainty-aware 3D human body pose estimation is key to enabling truly safe but efficient human-robot interactions. Current uncertainty-aware methods in 3D human pose estimation are limited to predicting the uncertainty of…

Estimating a 3D human pose has proven to be a challenging task, primarily because of the complexity of the human body joints, occlusions, and variability in lighting conditions. In this paper, we introduce a higher-order graph convolutional…

We describe a method for 3D human pose estimation from transient images (i.e., a 3D spatio-temporal histogram of photons) acquired by an optical non-line-of-sight (NLOS) imaging system. Our method can perceive 3D human pose by `looking…

Previous learning based hand pose estimation methods does not fully exploit the prior information in hand model geometry. Instead, they usually rely a separate model fitting step to generate valid hand poses. Such a post processing is…

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure…

Recent 3D-based manipulation methods either directly predict the grasp pose using 3D neural networks, or solve the grasp pose using similar objects retrieved from shape databases. However, the former faces generalizability challenges when…

Human motion prediction aims to forecast future human poses given a historical motion. Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to…

Normalizing flows (NF) are a class of powerful generative models that have gained popularity in recent years due to their ability to model complex distributions with high flexibility and expressiveness. In this work, we introduce a new type…

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they…