Zobrazeno 1 - 10
of 1 252
pro vyhledávání: '"Li, Weijia"'
Autor:
Zhou, Baichuan, Yang, Haote, Chen, Dairong, Ye, Junyan, Bai, Tianyi, Yu, Jinhua, Zhang, Songyang, Lin, Dahua, He, Conghui, Li, Weijia
Recent evaluations of Large Multimodal Models (LMMs) have explored their capabilities in various domains, with only few benchmarks specifically focusing on urban environments. Moreover, existing urban benchmarks have been limited to evaluating LMMs w
Externí odkaz:
http://arxiv.org/abs/2408.17267
Autor:
Li, Weijia, He, Jun, Ye, Junyan, Zhong, Huaping, Zheng, Zhimeng, Huang, Zilong, Lin, Dahua, He, Conghui
Satellite-to-street view synthesis aims at generating a realistic street-view image from its corresponding satellite-view image. Although stable diffusion models have exhibit remarkable performance in a variety of image generation applications, their
Externí odkaz:
http://arxiv.org/abs/2408.14765
Autor:
Li, Weijia, Yu, Jinhua, Chen, Dairong, Lin, Yi, Dong, Runmin, Zhang, Xiang, He, Conghui, Fu, Haohuan
In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning, broadening its
Externí odkaz:
http://arxiv.org/abs/2408.09460
Cross-view geolocalization identifies the geographic location of street view images by matching them with a georeferenced satellite database. Significant challenges arise due to the drastic appearance and geometry differences between views. In this p
Externí odkaz:
http://arxiv.org/abs/2408.05475
Street-to-satellite image synthesis focuses on generating realistic satellite images from corresponding ground street-view images while maintaining a consistent content layout, similar to looking down from the sky. The significant differences in pers
Externí odkaz:
http://arxiv.org/abs/2408.01812
Single-image dehazing is a pivotal challenge in computer vision that seeks to remove haze from images and restore clean background details. Recognizing the limitations of traditional physical model-based methods and the inefficiencies of current atte
Externí odkaz:
http://arxiv.org/abs/2407.11505
We present Ksformer, utilizing Multi-scale Key-select Routing Attention (MKRA) for intelligent selection of key areas through multi-channel, multi-scale windows with a top-k operator, and Lightweight Frequency Processing Module (LFPM) to enhance high
Externí odkaz:
http://arxiv.org/abs/2406.19703
Real-world application models are commonly deployed in dynamic environments, where the target domain distribution undergoes temporal changes. Continual Test-Time Adaptation (CTTA) has recently emerged as a promising technique to gradually adapt a sou
Externí odkaz:
http://arxiv.org/abs/2406.16439
Autor:
Zhang, Lixian, Zhao, Yi, Dong, Runmin, Zhang, Jinxiao, Yuan, Shuai, Cao, Shilei, Chen, Mengxuan, Zheng, Juepeng, Li, Weijia, Liu, Wei, Zhang, Wayne, Feng, Litong, Fu, Haohuan
Vast amounts of remote sensing (RS) data provide Earth observations across multiple dimensions, encompassing critical spatial, temporal, and spectral information which is essential for addressing global-scale challenges such as land use monitoring, d
Externí odkaz:
http://arxiv.org/abs/2406.08079
The objective of single image dehazing is to restore hazy images and produce clear, high-quality visuals. Traditional convolutional models struggle with long-range dependencies due to their limited receptive field size. While Transformers excel at ca
Externí odkaz:
http://arxiv.org/abs/2405.05811