Related papers: Self-Supervision and Spatial-Sequential Attention …
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…
3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D labels, which are expensive and labor-intensive. To tackle the…
Current Human Pose Estimation methods have achieved significant improvements. However, state-of-the-art models ignore out-of-image keypoints and use uncalibrated heatmaps as keypoint location representations. To address these limitations,…
We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression…
Multi-person pose estimation (MPPE) in natural images is key to the meaningful use of visual data in many fields including movement science, security, and rehabilitation. In this paper we tackle MPPE with a bottom-up approach, starting with…
Multi-person pose estimation (MPPE), which aims to locate the key points for all persons in the frames, is an active research branch of computer vision. Variable human poses and complex scenes make MPPE dependent on local details and global…
Human pose estimation in complicated situations has always been a challenging task. Many Transformer-based pose networks have been proposed recently, achieving encouraging progress in improving performance. However, the remarkable…
Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such…
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses. In this…
A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL). Considering these in mind, to suit the…
High-resolution representation is necessary for human pose estimation to achieve high performance, and the ensuing problem is high computational complexity. In particular, predominant pose estimation methods estimate human joints by 2D…
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.…
Human in-bed pose estimation has huge practical values in medical and healthcare applications yet still mainly relies on expensive pressure mapping (PM) solutions. In this paper, we introduce our novel physics inspired vision-based approach…
We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns the types of coherence modelled. Consistency is maximised…
Accurate 3D human pose estimation (3D HPE) is crucial for enabling autonomous vehicles (AVs) to make informed decisions and respond proactively in critical road scenarios. Promising results of 3D HPE have been gained in several domains such…
Deducing a 3D human pose from a single 2D image is inherently challenging because multiple 3D poses can correspond to the same 2D representation. 3D data can resolve this pose ambiguity, but it is expensive to record and requires an…
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…
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…
Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the…
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…