Zobrazeno 1 - 10
of 345
pro vyhledávání: '"WANG Haoqian"'
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 6, Pp 238-244 (2024)
Objective Over-excavation in tunnel construction, mainly caused by inappropriate blasting,will affect the smooth progress and safety of tunnel excavation, increase construction cost and reduce economic benefits. In order to radically solve this probl
Externí odkaz:
https://doaj.org/article/4be018dc7063440ab9e57244d840e70c
Compared with previous 3D reconstruction methods like Nerf, recent Generalizable 3D Gaussian Splatting (G-3DGS) methods demonstrate impressive efficiency even in the sparse-view setting. However, the promising reconstruction performance of existing G
Externí odkaz:
http://arxiv.org/abs/2408.13770
Autor:
Hu, Xiaowan, Chen, Yiyi, Li, Yan, Wang, Minquan, Wang, Haoqian, Chen, Quan, Li, Han, Jiang, Peng
With the rapid expansion of e-commerce, more consumers have become accustomed to making purchases via livestreaming. Accurately identifying the products being sold by salespeople, i.e., livestreaming product retrieval (LPR), poses a fundamental and d
Externí odkaz:
http://arxiv.org/abs/2407.16248
We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RGB-D methods suffer from scale ambiguity due to missing or imprecise de
Externí odkaz:
http://arxiv.org/abs/2407.06984
Recently,3DGaussianSplattinghasshowngreatpotentialin visual Simultaneous Localization And Mapping (SLAM). Existing methods have achieved encouraging results on RGB-D SLAM, but studies of the monocular case are still scarce. Moreover, they also fail t
Externí odkaz:
http://arxiv.org/abs/2405.13748
This paper presents a novel self-supervised two-frame multi-camera metric depth estimation network, termed M${^2}$Depth, which is designed to predict reliable scale-aware surrounding depth in autonomous driving. Unlike the previous works that use mul
Externí odkaz:
http://arxiv.org/abs/2405.02004
To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabulary and associates body poses with texture maps for animation. Given mul
Externí odkaz:
http://arxiv.org/abs/2404.00524
Novel view synthesis from unconstrained in-the-wild images remains a meaningful but challenging task. The photometric variation and transient occluders in those unconstrained images make it difficult to reconstruct the original scene accurately. Prev
Externí odkaz:
http://arxiv.org/abs/2403.15704
Multi-view compression technology, especially Stereo Image Compression (SIC), plays a crucial role in car-mounted cameras and 3D-related applications. Interestingly, the Distributed Source Coding (DSC) theory suggests that efficient data compression
Externí odkaz:
http://arxiv.org/abs/2312.16963
Humans live in a 3D world and commonly use natural language to interact with a 3D scene. Modeling a 3D language field to support open-ended language queries in 3D has gained increasing attention recently. This paper introduces LangSplat, which constr
Externí odkaz:
http://arxiv.org/abs/2312.16084