Zobrazeno 1 - 10
of 3 890
pro vyhledávání: '"Luo, Lei"'
Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupervised flow network that also leverages object information from the la
Externí odkaz:
http://arxiv.org/abs/2405.02608
Greenspaces are tightly linked to human well-being. Yet, rapid urbanization has exacerbated greenspace exposure inequality and declining human life quality. Roof greening has been recognized as an effective strategy to mitigate these negative impacts
Externí odkaz:
http://arxiv.org/abs/2404.13692
Establishing reliable correspondences is essential for registration tasks such as 3D and 2D3D registration. Existing methods commonly leverage geometric or semantic point features to generate potential correspondences. However, these features may fac
Externí odkaz:
http://arxiv.org/abs/2403.19919
Efficiently finding optimal correspondences between point clouds is crucial for solving both rigid and non-rigid point cloud registration problems. Existing methods often rely on geometric or semantic feature embedding to establish correspondences an
Externí odkaz:
http://arxiv.org/abs/2401.00436
The vast majority of standard image and video content available online is represented in display-encoded color spaces, in which pixel values are conveniently scaled to a limited range (0-1) and the color distribution is approximately perceptually uni
Externí odkaz:
http://arxiv.org/abs/2312.03640
Point Cloud Registration (PCR) is a critical and challenging task in computer vision. One of the primary difficulties in PCR is identifying salient and meaningful points that exhibit consistent semantic and geometric properties across different scans
Externí odkaz:
http://arxiv.org/abs/2309.06207
Developments in three-dimensional real worlds promote the integration of geoinformation and building information models (BIM) known as GeoBIM in urban construction. Light detection and ranging (LiDAR) integrated with global navigation satellite syste
Externí odkaz:
http://arxiv.org/abs/2304.11719
Autor:
Jung, Hyunyoung, Hui, Zhuo, Luo, Lei, Yang, Haitao, Liu, Feng, Yoo, Sungjoo, Ranjan, Rakesh, Demandolx, Denis
To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs. However, downsizing inputs makes the estimation more challenging because objects and motion ranges become small
Externí odkaz:
http://arxiv.org/abs/2303.16493
Autor:
Wu, Qianliang, Shen, Yaqi, Jiang, Haobo, Mei, Guofeng, Ding, Yaqing, Luo, Lei, Xie, Jin, Yang, Jian
Point Cloud Registration is a fundamental and challenging problem in 3D computer vision. Recent works often utilize the geometric structure information in point feature embedding or outlier rejection for registration while neglecting to consider expl
Externí odkaz:
http://arxiv.org/abs/2302.05844
Autor:
Li, Zheng, Li, Xiang, Yang, Lingfeng, Zhao, Borui, Song, Renjie, Luo, Lei, Li, Jun, Yang, Jian
Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two di
Externí odkaz:
http://arxiv.org/abs/2211.16231