Related papers: Pose Transformers (POTR): Human Motion Prediction …
Human motion prediction from motion capture data is a classical problem in the computer vision, and conventional methods take the holistic human body as input. These methods ignore the fact that, in various human activities, different body…
We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We present a cascade of such DNN regressors which results in high…
Object pose estimation is a key perceptual capability in robotics. We propose a fully-convolutional extension of the PoseCNN method, which densely predicts object translations and orientations. This has several advantages such as improving…
We propose a new representation of human body motion which encodes a full motion in a sequence of latent motion primitives. Recently, task generic motion priors have been introduced and propose a coherent representation of human motion…
Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this paper, we present a new pose-based convolutional neural network model…
3D representation and reconstruction of human bodies have been studied for a long time in computer vision. Traditional methods rely mostly on parametric statistical linear models, limiting the space of possible bodies to linear…
Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing…
State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction…
We present Pose-NDF, a continuous model for plausible human poses based on neural distance fields (NDFs). Pose or motion priors are important for generating realistic new poses and for reconstructing accurate poses from noisy or partial…
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…
Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance. While there is a lot of research on coarse-grained (human center prediction) and…
Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem.Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D…
We propose a new deep learning network that introduces a deeper CNN channel filter and constraints as losses to reduce joint position and motion errors for 3D video human body pose estimation. Our model outperforms the previous best result…
Predicting trajectories of pedestrians is quintessential for autonomous robots which share the same environment with humans. In order to effectively and safely interact with humans, trajectory prediction needs to be both precise and…
In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our…
Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the large view variations in captured human actions. We propose a novel view…
Short-term human pose prediction plays a crucial role in interactive systems, assistive robots, and emotion-aware human-computer interaction[1-3]. While current trajectory prediction models primarily rely on geometric motion cues, they…
Can freely moving humans or animals themselves serve as calibration targets for multi-camera systems while simultaneously estimating their correspondences across views? We humans can solve this problem by mentally rotating the observed 2D…
The self-attention mechanism in Transformer architecture, invariant to sequence order, necessitates positional embeddings to encode temporal order in time series prediction. We argue that this reliance on positional embeddings restricts the…
We tackle the problem of Human Locomotion Forecasting, a task for jointly predicting the spatial positions of several keypoints on the human body in the near future under an egocentric setting. In contrast to the previous work that aims to…