Zobrazeno 1 - 10
of 1 626
pro vyhledávání: '"Cao, Xun"'
Autor:
Zhuang, Yiyu, He, Yuxiao, Zhang, Jiawei, Wang, Yanwen, Zhu, Jiahe, Yao, Yao, Zhu, Siyu, Cao, Xun, Zhu, Hao
Creating 3D head avatars is a significant yet challenging task for many applicated scenarios. Previous studies have set out to learn 3D human head generative models using massive 2D image data. Although these models are highly generalizable for human
Externí odkaz:
http://arxiv.org/abs/2410.01226
Autor:
He, Qianyun, Ji, Xinya, Gong, Yicheng, Lu, Yuanxun, Diao, Zhengyu, Huang, Linjia, Yao, Yao, Zhu, Siyu, Ma, Zhan, Xu, Songcen, Wu, Xiaofei, Zhang, Zixiao, Cao, Xun, Zhu, Hao
We present a novel approach for synthesizing 3D talking heads with controllable emotion, featuring enhanced lip synchronization and rendering quality. Despite significant progress in the field, prior methods still suffer from multi-view consistency a
Externí odkaz:
http://arxiv.org/abs/2408.00297
Autor:
He, Yuxiao, Zhuang, Yiyu, Wang, Yanwen, Yao, Yao, Zhu, Siyu, Li, Xiaoyu, Zhang, Qi, Cao, Xun, Zhu, Hao
Creating a 360{\deg} parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in
Externí odkaz:
http://arxiv.org/abs/2408.00296
This paper introduces {HINER}, a novel neural representation for compressing HSI and ensuring high-quality downstream tasks on compressed HSI. HINER fully exploits inter-spectral correlations by explicitly encoding of spectral wavelengths and achieve
Externí odkaz:
http://arxiv.org/abs/2407.21395
Implicit Neural Representation (INR), which utilizes a neural network to map coordinate inputs to corresponding attributes, is causing a revolution in the field of signal processing. However, current INR techniques suffer from the "frequency"-specifi
Externí odkaz:
http://arxiv.org/abs/2407.19434
The integration of miniaturized spectrometers into mobile devices offers new avenues for image quality enhancement and facilitates novel downstream tasks. However, the broader application of spectral sensors in mobile photography is hindered by the i
Externí odkaz:
http://arxiv.org/abs/2407.17996
Representing signals using coordinate networks dominates the area of inverse problems recently, and is widely applied in various scientific computing tasks. Still, there exists an issue of spectral bias in coordinate networks, limiting the capacity t
Externí odkaz:
http://arxiv.org/abs/2407.17834
Implicit Neural Representation (INR) has become a popular method for representing visual signals (e.g., 2D images and 3D scenes), demonstrating promising results in various downstream applications. Given its potential as a medium for visual signals,
Externí odkaz:
http://arxiv.org/abs/2407.08457
Autor:
Wu, Shuang, Lin, Youtian, Zhang, Feihu, Zeng, Yifei, Xu, Jingxi, Torr, Philip, Cao, Xun, Yao, Yao
Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a native 3D gene
Externí odkaz:
http://arxiv.org/abs/2405.14832
Autor:
Yue, Wen-Cheng, Yuan, Zixiong, Huang, Peiyuan, Sun, Yizhe, Gao, Tan, Lyu, Yang-Yang, Tu, Xuecou, Dong, Sining, He, Liang, Dong, Ying, Cao, Xun, Kang, Lin, Wang, Huabing, Wu, Peiheng, Nisoli, Cristiano, Wang, Yong-Lei
Publikováno v:
Nature Nanotechnology (2024)
Ferrotoroidicity, the fourth form of primary ferroic order, breaks both space and time inversion symmetry. So far, direct observation of ferrotoroidicity in natural materials remains elusive, which impedes the exploration of ferrotoroidic phase trans
Externí odkaz:
http://arxiv.org/abs/2404.19377