Zobrazeno 1 - 10
of 18 838
pro vyhledávání: '"Song, Li"'
Autor:
Eid, I. S., Song, Li
As one of typical layered structures, antiferromagnetic CuCrP$_{2}$S$_{6}$ single crystal has high potential for magnetoelectric devices and spintronic multi-terminal chips due to its unique magnetic anisotropy. However, to tune the anisotropic magne
Externí odkaz:
http://arxiv.org/abs/2409.12509
While previous audio-driven talking head generation (THG) methods generate head poses from driving audio, the generated poses or lips cannot match the audio well or are not editable. In this study, we propose \textbf{PoseTalk}, a THG system that can
Externí odkaz:
http://arxiv.org/abs/2409.02657
Autor:
Guo, Shuai, Zhong, Houqiang, Wang, Qiuwen, Chen, Ziyu, Gao, Yijie, Yuan, Jiajing, Zhang, Chenyu, Xie, Rong, Song, Li
Recently, NVS in human-object interaction scenes has received increasing attention. Existing human-object interaction datasets mainly consist of static data with limited views, offering only RGB images or videos, mostly containing interactions betwee
Externí odkaz:
http://arxiv.org/abs/2409.12980
Autor:
Chen, Ziyu, Yang, Jiawei, Huang, Jiahui, de Lutio, Riccardo, Esturo, Janick Martinez, Ivanovic, Boris, Litany, Or, Gojcic, Zan, Fidler, Sanja, Pavone, Marco, Song, Li, Wang, Yue
We introduce OmniRe, a holistic approach for efficiently reconstructing high-fidelity dynamic urban scenes from on-device logs. Recent methods for modeling driving sequences using neural radiance fields or Gaussian Splatting have demonstrated the pot
Externí odkaz:
http://arxiv.org/abs/2408.16760
Recently, the dynamic scene reconstruction using Gaussians has garnered increased interest. Mainstream approaches typically employ a global deformation field to warp a 3D scene in the canonical space. However, the inherently low-frequency nature of i
Externí odkaz:
http://arxiv.org/abs/2408.13036
Parameter-efficient transfer learning (PETL) is a promising task, aiming to adapt the large-scale pre-trained model to downstream tasks with a relatively modest cost. However, current PETL methods struggle in compressing computational complexity and
Externí odkaz:
http://arxiv.org/abs/2407.14302
Volumetric video based on Neural Radiance Field (NeRF) holds vast potential for various 3D applications, but its substantial data volume poses significant challenges for compression and transmission. Current NeRF compression lacks the flexibility to
Externí odkaz:
http://arxiv.org/abs/2407.09026
Autor:
Yang, Zi-Xu, Zhang, Liang, Zhang, Shuang-Nan, Tao, L., Zhang, Shu, Ma, Ruican, Bu, Qingcui, Huang, Yue, Liu, He-Xin, Yu, Wei, Xiao, Guang C., Wang, Peng-Ju, Feng, Hua, Song, Li-Ming, Ma, Xiang, Ge, Mingyu, Zhao, QingChang, Qu, J. L.
We present an energy-dependent analysis for the type-C quasi-periodic oscillations (QPOs) observed in the black hole X-ray binary Swift J1727.8-1613 using Insight-HXMT observations. We find that the QPO fractional rms at energies above 40 keV is sign
Externí odkaz:
http://arxiv.org/abs/2407.05236
Realistic image restoration is a crucial task in computer vision, and the use of diffusion-based models for image restoration has garnered significant attention due to their ability to produce realistic results. However, the quality of the generated
Externí odkaz:
http://arxiv.org/abs/2407.03635
Autor:
Zhang, Yuhong, Zhang, Hengsheng, Chai, Xinning, Cheng, Zhengxue, Xie, Rong, Song, Li, Zhang, Wenjun
Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc. However, due to the inherent complexity and non-uniqueness of degradation
Externí odkaz:
http://arxiv.org/abs/2407.03636