SMPLest-X:用于表达人类姿势和形状估计的终极缩放
IEEE transactions on pattern analysis and machine intelligence
|October 7, 2025
概括
这项研究扩大了表达式的人类姿势和形状估计 (EHPS) 模型,使用各种数据和大型视觉变压器. 由此产生的基础模型在各种基准上实现了最先进的性能和适应性.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人与计算机的交互
背景情况:
- 目前的表达式人体姿势和形状估计 (EHPS) 方法受限于有限的数据集和建筑创新.
- 扩展EHPS对于更广泛的应用至关重要,但需要广泛的数据和模型容量.
研究的目的:
- 调查数据和模型缩放对表达式人类姿势和形状估计 (EHPS) 的影响.
- 为EHPS开发具有强大的性能和可转移性的通用基础模型.
主要方法:
- 对40个EHPS数据集进行系统的调查,以扩大数据规模,确定最佳的培训方案和数据源.
- 使用视觉变压器 (高达ViT-Huge) 和极简主义架构 (SMPLer-X,SMPLest-X) 来进行模型缩放.
- 制定了微调策略,以将通用基础模型适应到专业模型中.
主要成果:
- 在来自不同来源的1000万个培训实例中,在EHPS绩效方面取得了下降的回报.
- 基金会模型在各种基准测试中表现出强的表现,并且可以很好地转移到未见的环境中.
- 精细调整的模型实现了进一步的性能提升,在7个基准上提供了最先进的结果,包括AGORA,UBody,EgoBody和SynHand.
结论:
- 数据和模型的缩放显著增强了EHPS的能力,导致了通用基础模型.
- 这些基础模型提供了强大的性能和适应性,优于以前的先进方法.
- 拟议的微调策略有效地专门化了通用模型,以提高特定任务的性能.
更多相关视频
05:49Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
Published on: November 1, 2024
1.2K
06:32Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
Published on: July 14, 2023
1.8K
相关概念视频
01:26Scaling
557
In designing and analyzing filters, resonant circuits, or circuit analysis at large, working with standard element values like 1 ohm, 1 henry, or 1 farad can be convenient before scaling these values to more realistic figures. This approach is widely utilized by not employing realistic element values in numerous examples and problems; it simplifies mastering circuit analysis through convenient component values. The complexity of calculations is thereby reduced, with the understanding that...
557
01:14Muscles for Facial Expressions
4.7K
The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
4.7K
01:05Estimation of the Physical Quantities
7.2K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
7.2K