Zobrazeno 1 - 10
of 546
pro vyhledávání: '"Wetzstein, Gordon"'
Volume parameterizations abound in recent literature, from the classic voxel grid to the implicit neural representation and everything in between. While implicit representations have shown impressive capacity and better memory efficiency compared to
Externí odkaz:
http://arxiv.org/abs/2411.13525
Autor:
Chen, Hansheng, Shen, Bokui, Liu, Yulin, Shi, Ruoxi, Zhou, Linqi, Lin, Connor Z., Gu, Jiayuan, Su, Hao, Wetzstein, Gordon, Guibas, Leonidas
Multi-view image diffusion models have significantly advanced open-domain 3D object generation. However, most existing models rely on 2D network architectures that lack inherent 3D biases, resulting in compromised geometric consistency. To address th
Externí odkaz:
http://arxiv.org/abs/2410.18974
Autor:
Li, Zilu, Yang, Guandao, Zhao, Qingqing, Deng, Xi, Guibas, Leonidas, Hariharan, Bharath, Wetzstein, Gordon
Publikováno v:
SIGGRAPH Conference Papers 2024
This paper presents a method to leverage arbitrary neural network architecture for control variates. Control variates are crucial in reducing the variance of Monte Carlo integration, but they hinge on finding a function that both correlates with the
Externí odkaz:
http://arxiv.org/abs/2409.15394
Autor:
Je, Jihyeon, Liu, Jiayi, Yang, Guandao, Deng, Boyang, Cai, Shengqu, Wetzstein, Gordon, Litany, Or, Guibas, Leonidas
Symmetries are ubiquitous across all kinds of objects, whether in nature or in man-made creations. While these symmetries may seem intuitive to the human eye, detecting them with a machine is nontrivial due to the vast search space. Classical geometr
Externí odkaz:
http://arxiv.org/abs/2410.02786
Emerging holographic display technology offers unique capabilities for next-generation virtual reality systems. Current holographic near-eye displays, however, only support a small \'etendue, which results in a direct tradeoff between achievable fiel
Externí odkaz:
http://arxiv.org/abs/2409.03143
Autor:
Yang, Shuai, Tan, Jing, Zhang, Mengchen, Wu, Tong, Li, Yixuan, Wetzstein, Gordon, Liu, Ziwei, Lin, Dahua
3D immersive scene generation is a challenging yet critical task in computer vision and graphics. A desired virtual 3D scene should 1) exhibit omnidirectional view consistency, and 2) allow for free exploration in complex scene hierarchies. Existing
Externí odkaz:
http://arxiv.org/abs/2408.13252
Thermal imaging has a variety of applications, from agricultural monitoring to building inspection to imaging under poor visibility, such as in low light, fog, and rain. However, reconstructing thermal scenes in 3D presents several challenges due to
Externí odkaz:
http://arxiv.org/abs/2407.15337
Autor:
Xu, Mengda, Xu, Zhenjia, Xu, Yinghao, Chi, Cheng, Wetzstein, Gordon, Veloso, Manuela, Song, Shuran
We present Im2Flow2Act, a scalable learning framework that enables robots to acquire real-world manipulation skills without the need of real-world robot training data. The key idea behind Im2Flow2Act is to use object flow as the manipulation interfac
Externí odkaz:
http://arxiv.org/abs/2407.15208
Autor:
Deng, Boyang, Tucker, Richard, Li, Zhengqi, Guibas, Leonidas, Snavely, Noah, Wetzstein, Gordon
We present a method for generating Streetscapes-long sequences of views through an on-the-fly synthesized city-scale scene. Our generation is conditioned by language input (e.g., city name, weather), as well as an underlying map/layout hosting the de
Externí odkaz:
http://arxiv.org/abs/2407.13759
Autor:
Chen, Hang, Gao, Sheng, Zhao, Zejia, Duan, Zhengyang, Zhang, Haiou, Wetzstein, Gordon, Lin, Xing
Optical super-oscillation enables far-field super-resolution imaging beyond diffraction limits. However, the existing super-oscillatory lens for the spatial super-resolution imaging system still confronts critical limitations in performance due to th
Externí odkaz:
http://arxiv.org/abs/2406.19126