Zobrazeno 1 - 10
of 849
pro vyhledávání: '"Wang, Zhisheng"'
Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into multiple lay
Externí odkaz:
http://arxiv.org/abs/2410.15749
For extending CT field-of-view to perform non-destructive testing, the Symmetric Multi-Linear trajectory Computed Tomography (SMLCT) has been developed as a successful example of non-standard CT scanning modes. However, inevitable geometric errors ca
Externí odkaz:
http://arxiv.org/abs/2408.15069
Autor:
Li, Weiqin, Yang, Peiji, Zhong, Yicheng, Zhou, Yixuan, Wang, Zhisheng, Wu, Zhiyong, Wu, Xixin, Meng, Helen
Spontaneous style speech synthesis, which aims to generate human-like speech, often encounters challenges due to the scarcity of high-quality data and limitations in model capabilities. Recent language model-based TTS systems can be trained on large,
Externí odkaz:
http://arxiv.org/abs/2407.13509
In this study, we propose AniPortrait, a novel framework for generating high-quality animation driven by audio and a reference portrait image. Our methodology is divided into two stages. Initially, we extract 3D intermediate representations from audi
Externí odkaz:
http://arxiv.org/abs/2403.17694
Neural radiance fields (NeRFs) are promising 3D representations for scenes, objects, and humans. However, most existing methods require multi-view inputs and per-scene training, which limits their real-life applications. Moreover, current methods foc
Externí odkaz:
http://arxiv.org/abs/2401.00979
Current parametric models have made notable progress in 3D hand pose and shape estimation. However, due to the fixed hand topology and complex hand poses, current models are hard to generate meshes that are aligned with the image well. To tackle this
Externí odkaz:
http://arxiv.org/abs/2312.15916
Recently, linear computed tomography (LCT) systems have actively attracted attention. To weaken projection truncation and image the region of interest (ROI) for LCT, the backprojection filtration (BPF) algorithm is an effective solution. However, in
Externí odkaz:
http://arxiv.org/abs/2309.11858
The objective of stylized speech-driven facial animation is to create animations that encapsulate specific emotional expressions. Existing methods often depend on pre-established emotional labels or facial expression templates, which may limit the ne
Externí odkaz:
http://arxiv.org/abs/2308.14448
Dancing with music is always an essential human art form to express emotion. Due to the high temporal-spacial complexity, long-term 3D realist dance generation synchronized with music is challenging. Existing methods suffer from the freezing problem
Externí odkaz:
http://arxiv.org/abs/2308.11945
This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV). Under the larger FOVs, the previously proposed backprojection filtration (BPF)
Externí odkaz:
http://arxiv.org/abs/2305.19767