相关论文: Uncertainty-Aware Testing-Time Optimization for 3D…

We present a method for learning to satisfy uncertain constraints from demonstrations. Our method uses robust optimization to obtain a belief over the potentially infinite set of possible constraints consistent with the demonstrations, and…

Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests. In fact, completing this task is quite challenging due to the diverse appearances,…

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…

3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective combination of 2D…

Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex environments. However, emerging autonomous edge robotics…

AI inference scaling is often tuned through 1D heuristics (a fixed reasoning pass) or 2D bivariate trade-offs (e.g., accuracy vs. compute), which fail to consider cost and latency constraints. We introduce a 3D optimization framework that…

For the current 3D human pose estimation task, a group of methods mainly learn the rules of 2D-3D projection from spatial and temporal correlation. However, earlier methods model the global features of the entire body joint in the time…

3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g.,…

Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated…

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…

Reliable localization is critical for robot navigation in complex indoor environments. In this paper, we propose an uncertainty-aware localization method that enhances the reliability of localization outputs without modifying the prediction…

We propose a new self-supervised method for predicting 3D human body pose from a single image. The prediction network is trained from a dataset of unlabelled images depicting people in typical poses and a set of unpaired 2D poses. By…

Low-visibility scenarios, such as low-light conditions, pose significant challenges to human pose estimation due to the scarcity of annotated low-light datasets and the loss of visual information under poor illumination. Recent domain…

This paper focuses on Human-Object Interaction (HOI) detection, addressing the challenge of identifying and understanding the interactions between humans and objects within a given image or video frame. Spearheaded by Detection Transformer…

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they…

Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on…

3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalization is employed. Current methodologies in domain…

3D human pose estimation involves reconstructing the human skeleton by detecting the body joints. Accurate and efficient solutions are required for several real-world applications including animation, human-robot interaction, surveillance,…

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…

There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. However, existing transformer-based methods treat body joints as…