Zobrazeno 1 - 10
of 934
pro vyhledávání: '"Wang, Shaofei"'
Recent advances in generative diffusion models have enabled the previously unfeasible capability of generating 3D assets from a single input image or a text prompt. In this work, we aim to enhance the quality and functionality of these models for the
Externí odkaz:
http://arxiv.org/abs/2401.04728
We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but often req
Externí odkaz:
http://arxiv.org/abs/2312.09228
We present IntrinsicAvatar, a novel approach to recovering the intrinsic properties of clothed human avatars including geometry, albedo, material, and environment lighting from only monocular videos. Recent advancements in human-based neural renderin
Externí odkaz:
http://arxiv.org/abs/2312.05210
Recent advances in large language models (LLMs) have opened new possibilities for artificial intelligence applications in finance. In this paper, we provide a practical survey focused on two key aspects of utilizing LLMs for financial tasks: existing
Externí odkaz:
http://arxiv.org/abs/2311.10723
We present a novel method for populating 3D indoor scenes with virtual humans that can navigate in the environment and interact with objects in a realistic manner. Existing approaches rely on training sequences that contain captured human motions and
Externí odkaz:
http://arxiv.org/abs/2305.12411
Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images, which has no
Externí odkaz:
http://arxiv.org/abs/2301.09299
Combining human body models with differentiable rendering has recently enabled animatable avatars of clothed humans from sparse sets of multi-view RGB videos. While state-of-the-art approaches achieve realistic appearance with neural radiance fields
Externí odkaz:
http://arxiv.org/abs/2210.10036
Synthesizing natural interactions between virtual humans and their 3D environments is critical for numerous applications, such as computer games and AR/VR experiences. Our goal is to synthesize humans interacting with a given 3D scene controlled by h
Externí odkaz:
http://arxiv.org/abs/2207.12824
Autor:
Gai, Tao, Jiang, Jiaolai, Wang, Shaofei, Ren, Yiming, Yang, Shanli, Qin, Zhen, Shao, Lang, Wu, Qian, Zhang, Jun, Liao, Junsheng
Publikováno v:
In Analytica Chimica Acta 8 August 2024 1316
Autor:
Wang, Shaofei, Yang, Min, Gao, Xiaodong, Li, Bin, Cai, Yaohui, Li, Changjian, He, Hailong, Zhao, Xining
Publikováno v:
In Agricultural and Forest Meteorology 15 July 2024 354