Zobrazeno 1 - 10
of 1 188
pro vyhledávání: '"Wang, Ti"'
Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial info
Externí odkaz:
http://arxiv.org/abs/2410.15582
The limited robustness of 3D Gaussian Splatting (3DGS) to motion blur and camera noise, along with its poor real-time performance, restricts its application in robotic SLAM tasks. Upon analysis, the primary causes of these issues are the density of v
Externí odkaz:
http://arxiv.org/abs/2405.19614
Traffic flow prediction is an essential task in constructing smart cities and is a typical Multivariate Time Series (MTS) Problem. Recent research has abandoned Gated Recurrent Units (GRU) and utilized dilated convolutions or temporal slicing for fea
Externí odkaz:
http://arxiv.org/abs/2404.11854
Although data-driven methods have achieved success in 3D human pose estimation, they often suffer from domain gaps and exhibit limited generalization. In contrast, optimization-based methods excel in fine-tuning for specific cases but are generally i
Externí odkaz:
http://arxiv.org/abs/2402.02339
Publikováno v:
Shanghai Jiaotong Daxue xuebao, Vol 58, Iss 9, Pp 1381-1389 (2024)
Fault diagnosis in power distribution networks is crucial for fault location, enhancement of fault processing efficiency, and reduction of power outage losses. Currently, the impact of switch operations and other interferences is seldomly considered
Externí odkaz:
https://doaj.org/article/85f2a49d8dc44c388be84d171276fd31
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 complex pose a
Externí odkaz:
http://arxiv.org/abs/2308.10305
Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations. To address this issue, we propose a novel
Externí odkaz:
http://arxiv.org/abs/2304.14045
3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-
Externí odkaz:
http://arxiv.org/abs/2303.05652
Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at capturing local details and lack prior knowledge of human body configura
Externí odkaz:
http://arxiv.org/abs/2206.06420
Publikováno v:
In Knowledge-Based Systems 9 October 2024 301