双筒深度估计中的主动视觉:一个自上而下的视角
Matteo Priorelli1, Giovanni Pezzulo2, Ivilin Peev Stoianov1
1Institute of Cognitive Sciences and Technologies, National Research Council of Italy, 35137 Padova, Italy.
Biomimetics (Basel, Switzerland)
|September 27, 2023
概括
这项研究提出了深度估计的积极推断,模拟大脑.
科学领域:
- 计算神经科学是一种计算神经科学.
- 计算机视觉 计算机视觉 计算机视觉
背景情况:
- 深度估计是一个复杂的问题,因为视觉模两可.
- 大脑使用各种线索 (单眼,双眼) 来进行深度感知.
- 目前的深度学习模型将大脑视为特征探测器,缺乏生物可信性.
研究的目的:
- 为深度估计提出一种新的,生物学上可信的方法.
- 将深度估计作为一个主动推理问题的框架.
- 通过生成模型和预测编码来研究大脑如何推断深度.
主要方法:
- 开发了一种层次性的生成模型,用于预测眼睛的投射.
- 采用了主动推理原理和模型逆转的预测编码.
- 纳入了一个非统一的fovea解决假设.
主要成果:
- 通过生物学上可信的同质转换证明了深度推断.
- 显示了主动视觉策略,结合固定和深度估计,提高准确性.
- 验证了使用局部消息传递的方法,适合神经电路.
结论:
- 积极推断为神经深度估计提供了一个生物学上可信的替代方案.
- 拟议的模型通过代循环整合了感知和行动.
- 这个框架支持高效的局部神经计算,用于深度感知.
相关概念视频
01:15Depth Perception and Spatial Vision
700
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
700
01:24Vision
53.5K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.5K