Related papers: Hourglass Tokenizer for Efficient Transformer-Base…

The existing human pose estimation methods are confronted with inaccurate long-distance regression or high computational cost due to the complex learning objectives. This work proposes a novel deep learning framework for human pose…

Reconstructing 3D human pose and shape from monocular videos is a well-studied but challenging problem. Common challenges include occlusions, the inherent ambiguities in the 2D to 3D mapping and the computational complexity of video…

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the…

Pose estimation is a critical task in computer vision with a wide range of applications from activity monitoring to human-robot interaction. However,most of the existing methods are computationally expensive or have complex architecture.…

We present MoVNect, a lightweight deep neural network to capture 3D human pose using a single RGB camera. To improve the overall performance of the model, we apply the teacher-student learning method based knowledge distillation to 3D human…

Estimating the 3D position of human joints has become a widely researched topic in the last years. Special emphasis has gone into defining novel methods that extrapolate 2-dimensional data (keypoints) into 3D, namely predicting the…

Despite the promising performance of current 3D human pose estimation techniques, understanding and enhancing their generalization on challenging in-the-wild videos remain an open problem. In this work, we focus on the robustness of…

Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. Although many sparse query-based methods have already attempted to improve the…

Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically…

Nowadays, Transformers and Graph Convolutional Networks (GCNs) are the prevailing techniques for 3D human pose estimation. However, Transformer-based methods either ignore the spatial neighborhood relationships between the joints when used…

In this paper, a real-time method called PoP-Net is proposed to predict multi-person 3D poses from a depth image. PoP-Net learns to predict bottom-up part representations and top-down global poses in a single shot. Specifically, a new…

Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the…

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective…

Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures…

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

Although vision transformers (ViTs) have shown promising results in various computer vision tasks recently, their high computational cost limits their practical applications. Previous approaches that prune redundant tokens have demonstrated…

Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the…

We propose a novel generative approach for 3D human pose estimation. 3D human pose estimation poses several key challenges due to the complex geometry of the human body, self-occluding joints, and the requirement for large-scale real-world…