Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Xu, Tianshuo"'
Autor:
Lu, Hao, Xu, Tianshuo, Zheng, Wenzhao, Zhang, Yunpeng, Zhan, Wei, Du, Dalong, Tomizuka, Masayoshi, Keutzer, Kurt, Chen, Yingcong
Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting their practic
Externí odkaz:
http://arxiv.org/abs/2412.09043
Autor:
Xu, Tianshuo, Chen, Zhifei, Wu, Leyi, Lu, Hao, Chen, Yuying, Jiang, Lihui, Liu, Bingbing, Chen, Yingcong
Recent numerous video generation models, also known as world models, have demonstrated the ability to generate plausible real-world videos. However, many studies have shown that these models often produce motion results lacking logical or physical co
Externí odkaz:
http://arxiv.org/abs/2412.00547
We explore Bird's-Eye View (BEV) generation, converting a BEV map into its corresponding multi-view street images. Valued for its unified spatial representation aiding multi-sensor fusion, BEV is pivotal for various autonomous driving applications. C
Externí odkaz:
http://arxiv.org/abs/2409.01014
Diffusion models (DMs) are a powerful generative framework that have attracted significant attention in recent years. However, the high computational cost of training DMs limits their practical applications. In this paper, we start with a consistency
Externí odkaz:
http://arxiv.org/abs/2404.07946
Autor:
Mi, Peng, Shen, Li, Ren, Tianhe, Zhou, Yiyi, Xu, Tianshuo, Sun, Xiaoshuai, Liu, Tongliang, Ji, Rongrong, Tao, Dacheng
Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss whe
Externí odkaz:
http://arxiv.org/abs/2306.17504
Autor:
Xu, Tianshuo, Li, Lijiang, Mi, Peng, Zheng, Xiawu, Chao, Fei, Ji, Rongrong, Tian, Yonghong, Shen, Qiang
PSNR-oriented models are a critical class of super-resolution models with applications across various fields. However, these models tend to generate over-smoothed images, a problem that has been analyzed previously from the perspectives of models or
Externí odkaz:
http://arxiv.org/abs/2201.01034
Autor:
Liu, Kaixin, Chen, Xiaolong, Zhang, Peng, Ma, Baosong, Feng, Xin, Zhang, Yunlong, Liu, Hao, Tan, Xuhong, Xu, Tianshuo
Publikováno v:
In Tunnelling and Underground Space Technology incorporating Trenchless Technology Research July 2024 149
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.