IGAF:增量引导注意力融合用于深度超分辨率.
Athanasios Tragakis1, Chaitanya Kaul2, Kevin J Mitchell1
1School of Physics and Astronomy, University of Glasgow, Glasgow G12 8QQ, UK.
Sensors (Basel, Switzerland)
|January 11, 2025
概括
本研究引入了一种用于指导深度超分辨率 (GDSR) 的新方法,以使用高分辨率图像来增强低分辨率深度图. 渐进指导注意力融合 (IGAF) 模块在深度地图增强方面取得了最先进的结果.
科学领域:
- 计算机视觉 计算机视觉
- 机器人技术 机器人技术 机器人技术
- 传感器融合式传感器
背景情况:
- 准确的深度估计对于机器人,导航和医学成像至关重要.
- 传统的深度传感器产生低分辨率 (LR) 的深度图,限制了详细的场景感知.
- 提高LR深度图以高分辨率 (HR) 使用RGB图像等结构化输入是必不可少的.
研究的目的:
- 为指导深度超分辨率 (GDSR) 提出一种新的传感器融合方法.
- 开发一个增量引导注意力融合 (IGAF) 模块,以实现有效的特征融合.
- 创建一个强大的超分辨率模型,从LR输入生成详细的HR深度图.
主要方法:
- 开发了一种用于导向深度超分辨率 (GDSR) 的新型传感器融合方法.
- 引入了增量引导注意力融合 (IGAF) 模块,以融合RGB图像和LR深度地图功能.
- 使用基准数据集IGAF模块构建和评估了一个超级分辨率模型.
主要成果:
- 与IGAF一起提出的GDSR模型在纽约大学v2数据集上获得了×4,×8和×16上样的最先进的结果.
- 该模型在Middlebury,Lu和RGB-D-D数据集的零射击设置中超过了所有基线模型.
- 通过LR深度和HR图像数据的有效融合,证明了准确的HR深度地图生成.
结论:
- IGAF模块有效地融合了RGB图像和LR深度图的特征,以准确地估计HR深度.
- 拟议的GDSR方法提供了一个强大的解决方案,以提高深度地图分辨率.
- 该方法在多个数据集中实现了卓越的性能,突出了其可概括性和有效性.
相关概念视频
Depth Perception and Spatial Vision
548
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.
548
Super-resolution Fluorescence Microscopy
6.9K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
6.9K


