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 …

Image instance segmentation involves labeling pixels of images with classes and instances,
which is one of the pivotal technologies in many domains, such as natural scenes …

Although no specific domain knowledge is considered in the design, plain vision
transformers have shown excellent performance in visual recognition tasks. However, little …

Given an image with multiple people, our goal is to directly regress the pose and shape of all
the people as well as their relative depth. Inferring the depth of a person in an image …

Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion
capture with numerous applications. Despite encouraging progress, current state-of-the-art …

Human pose is typically represented by a coordinate vector of body joints or their heatmap
embeddings. While easy for data processing, unrealistic pose estimates are admitted due to …

We introduce a real-time, high-resolution background replacement technique which
operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is …

While the accuracy of 3D human pose estimation from images has steadily improved on
benchmark datasets, the best methods still fail in many real-world scenarios. This suggests …

Human-centric perceptions (eg, pose estimation, human parsing, pedestrian detection,
person re-identification, etc.) play a key role in industrial applications of visual models. While …

Differently from 2D image datasets such as COCO, largescale human datasets with 3D
ground-truth annotations are very difficult to obtain in the wild. In this paper, we address this …