Related papers: Tracking People by Predicting 3D Appearance, Locat…

This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences. Based on Lie algebra pose representation, a novel self-projection mechanism is…

Most recent approaches to monocular 3D human pose estimation rely on Deep Learning. They typically involve regressing from an image to either 3D joint coordinates directly or 2D joint locations from which 3D coordinates are inferred. Both…

Acquiring the accurate 3-D position of a target person around a robot provides fundamental and valuable information that is applicable to a wide range of robotic tasks, including home service, navigation and entertainment. This paper…

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the…

In this paper, we present a method for real-time multi-person human pose estimation from video by utilizing convolutional neural networks. Our method is aimed for use case specific applications, where good accuracy is essential and…

This paper investigates long-term face tracking of a specific person given his/her face image in a single frame as a query in a video stream. Through taking advantage of pre-trained deep learning models on big data, a novel system is…

Estimating 3D human poses from video is a challenging problem. The lack of 3D human pose annotations is a major obstacle for supervised training and for generalization to unseen datasets. In this work, we address this problem by proposing a…

Occlusion is a long-standing problem that causes many modern tracking methods to be erroneous. In this paper, we address the occlusion problem by exploiting the current and future possible locations of the target object from its past…

Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D…

We introduce a free-viewpoint rendering method -- HumanNeRF -- that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the…

This paper presents the first study on forecasting human dynamics from static images. The problem is to input a single RGB image and generate a sequence of upcoming human body poses in 3D. To address the problem, we propose the 3D Pose…

Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be…

We present SpatialTrackerV2, a feed-forward 3D point tracking method for monocular videos. Going beyond modular pipelines built on off-the-shelf components for 3D tracking, our approach unifies the intrinsic connections between point…

Monocular egocentric human pose estimation is essential for ubiquitous activity monitoring. However, understanding the user's absolute location within the environment remains a challenge. Existing methods primarily focus on relative motion…

3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer…

Predicting future human behavior from an input human video is a useful task for applications such as autonomous driving and robotics. While most previous works predict a single future, multiple futures with different behavior can…

For a humanoid robot to make eye contact and initiate communication with a person, it is necessary to estimate the person's head position. However, eye contact becomes difficult due to the mechanical delay of the robot when the person is…

We present a simple, fast, and light-weight RNN based framework for forecasting future locations of humans in first person monocular videos. The primary motivation for this work was to design a network which could accurately predict future…

In this paper we address the problems of detecting objects of interest in a video and of estimating their locations, solely from the gaze directions of people present in the video. Objects can be indistinctly located inside or outside the…

We propose a novel framework for accurate 3D human pose estimation in combat sports using sparse multi-camera setups. Our method integrates robust multi-view 2D pose tracking via a transformer-based top-down approach, employing epipolar…