Related papers: Gravity as a Reference for Estimating a Person's H…

The number of static human poses is limited, it is hard to retrieve the exact videos using one single pose as the clue. However, with a pose sequence or a dynamic gesture as the keyword, retrieving specific videos becomes more feasible. We…

Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot…

Machine learning models for camera-based physiological measurement can have weak generalization due to a lack of representative training data. Body motion is one of the most significant sources of noise when attempting to recover the subtle…

We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is…

Forensic gait analysis can aid the investigation of crimes through comparing features of gait captured in video footage. Modelling the probative value of gait evidence requires an understanding of the variation of features of gait between…

Monocular depth estimation is an ill-posed problem as the same 2D image can be projected from infinite 3D scenes. Although the leading algorithms in this field have reported significant improvement, they are essentially geared to 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…

Advances in machine learning and wearable sensors offer new opportunities for capturing and analyzing human movement outside specialized laboratories. Accurate assessment of human movement under real-world conditions is essential for…

Current unsupervised 2D-3D human pose estimation (HPE) methods do not work in multi-person scenarios due to perspective ambiguity in monocular images. Therefore, we present one of the first studies investigating the feasibility of…

A longstanding goal in computer vision is to model motions from videos, while the representations behind motions, i.e. the invisible physical interactions that cause objects to deform and move, remain largely unexplored. In this paper, we…

Markerless motion capture algorithms require a 3D body with properly personalized skeleton dimension and/or body shape and appearance to successfully track a person. Unfortunately, many tracking methods consider model personalization a…

Learning robot control policies from human videos is a promising direction for scaling up robot learning. However, how to extract action knowledge (or action representations) from videos for policy learning remains a key challenge. Existing…

We address the challenge of accurate 3D human pose and shape estimation from monocular images. The key to accuracy and robustness lies in high-quality training data. Existing training datasets containing real images with pseudo ground truth…

Cross-view person matching and 3D human pose estimation in multi-camera networks are particularly difficult when the cameras are extrinsically uncalibrated. Existing efforts generally require large amounts of 3D data for training neural…

Accurately analyzing the motion parts and their motion attributes in dynamic environments is crucial for advancing key areas such as embodied intelligence. Addressing the limitations of existing methods that rely on dense multi-view images…

Current methods for generating human motion videos rely on extracting pose sequences from reference videos, which restricts flexibility and control. Additionally, due to the limitations of pose detection techniques, the extracted pose…

In this paper, we describe a method to capture nearly entirely spherical (360 degree) depth information using two adjacent frames from a single spherical video with motion parallax. After illustrating a spherical depth information retrieval…

We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video.…

This is a short note to announce the availability of some movies that may be useful in classroom discussions on the photographic appearance of objects moving at relativistic speeds. The images are based on special relativity with no account…

This paper deals with motion capture of kinematic chains (e.g. human skeletons) from monocular image sequences taken by uncalibrated cameras. We present a method based on projecting an observation into a kinematic chain space (KCS). An…