Related papers: FlexPose: Pose Distribution Adaptation with Limite…

3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints…

This paper proposes a statistical approach to 2D pose estimation from human images. The main problems with the standard supervised approach, which is based on a deep recognition (image-to-pose) model, are that it often yields anatomically…

3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can…

Monocular 3D human pose estimation (HPE) methods estimate the 3D positions of joints from individual images. Existing 3D HPE approaches often use the cropped image alone as input for their models. However, the relative depths of joints…

Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitigate the…

Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in these scenarios due to the lack of identifiable…

Pose transfer aims to transfer a given person into a specified posture, has recently attracted considerable attention. A typical pose transfer framework usually employs representative datasets to train a discriminative model, which is often…

One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by customized architectures, such as high-resolution…

We introduce a principled, data-driven approach for modeling a neural prior over human body poses using normalizing flows. Unlike heuristic or low-expressivity alternatives, our method leverages RealNVP to learn a flexible density over…

We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without…

Person image synthesis, e.g., pose transfer, is a challenging problem due to large variation and occlusion. Existing methods have difficulties predicting reasonable invisible regions and fail to decouple the shape and style of clothing,…

Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead…

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,…

Diffusion models have demonstrated impressive capabilities in modeling complex data distributions and are increasingly applied in various generative tasks. In this work, we propose Pose Analysis by Diffusion Synthesis PADS, a unified…

Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also…

Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically…

Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across images. Existing datasets frequently lack diversity and…

We propose a novel pose-guided appearance transfer network for transferring a given reference appearance to a target pose in unprecedented image resolution (1024 * 1024), given respectively an image of the reference and target person. No 3D…

This work proposes an end-to-end neural interactive keypoint detection framework named Click-Pose, which can significantly reduce more than 10 times labeling costs of 2D keypoint annotation compared with manual-only annotation. Click-Pose…

Human pose estimators are typically retrained from scratch or naively fine-tuned whenever keypoint sets, sensing modalities, or deployment domains change--an inefficient, compute-intensive practice that rarely matches field constraints. We…