Zobrazeno 1 - 10
of 19 245
pro vyhledávání: '"SONG, Li"'
Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for h
Externí odkaz:
http://arxiv.org/abs/2412.13061
Autor:
Zhou, Chuqin, Lu, Guo, Li, Jiangchuan, Chen, Xiangyu, Cheng, Zhengxue, Song, Li, Zhang, Wenjun
Neural image compression often faces a challenging trade-off among rate, distortion and perception. While most existing methods typically focus on either achieving high pixel-level fidelity or optimizing for perceptual metrics, we propose a novel app
Externí odkaz:
http://arxiv.org/abs/2412.11379
Autor:
Hu, Qiang, Zhong, Houqiang, Zheng, Zihan, Zhang, Xiaoyun, Cheng, Zhengxue, Song, Li, Zhai, Guangtao, Wang, Yanfeng
Neural Radiance Field (NeRF)-based volumetric video has revolutionized visual media by delivering photorealistic Free-Viewpoint Video (FVV) experiences that provide audiences with unprecedented immersion and interactivity. However, the substantial da
Externí odkaz:
http://arxiv.org/abs/2412.11362
The widespread use of image acquisition technologies, along with advances in facial recognition, has raised serious privacy concerns. Face de-identification usually refers to the process of concealing or replacing personal identifiers, which is regar
Externí odkaz:
http://arxiv.org/abs/2411.09863
The neural radiance fields (NeRF) have advanced the development of 3D volumetric video technology, but the large data volumes they involve pose significant challenges for storage and transmission. To address these problems, the existing solutions typ
Externí odkaz:
http://arxiv.org/abs/2411.05322
In streaming media services, video transcoding is a common practice to alleviate bandwidth demands. Unfortunately, traditional methods employing a uniform rate factor (RF) across all videos often result in significant inefficiencies. Content-adaptive
Externí odkaz:
http://arxiv.org/abs/2411.05295
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