适应性内核 卷积式立体声匹配 经常性网络
Jiamian Wang1,2, Haijiang Sun1, Ping Jia1,2
1Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China.
Sensors (Basel, Switzerland)
|November 27, 2024
概括
这项研究引入了一种新的深度循环网络,用于立体匹配,通过自适应的内核卷曲和匹配注意力来提高成本体积的精细化. 新的AKC-Stereo网络显著提高了对基准数据集差异估计的准确性.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习 (Deep Learning) 是一种深度学习.
- 人工智能的人工智能
背景情况:
- 目前的高级立体声匹配依赖于使用Gated Recurrent Units (GRUs) 的代结构.
- 现有的基于GRU的方法往往缺乏成本量中的非本地几何和上下文信息.
- 这种限制阻碍了表现,特别是在复杂的场景中.
研究的目的:
- 为立体匹配提出一种新的深度循环网络架构.
- 通过结合自适应的内核卷积和注意力机制来增强成本体积表示.
- 为了提高双眼立体匹配的准确性和概括能力.
主要方法:
- 开发了一个基于GRU代的自适应内核卷积深度反复网络 (AKC-立体声).
- 引入了基于内核卷积的自适应式多尺度金字塔聚合 (KAP) 模块,以捕获空间相关性.
- 整合了一个匹配注意力 (MAR) 模块,以在代更新之前完善成本量.
主要成果:
- 与基本网络相比,AKC-立体声网络表现出更高的性能.
- 在Sceneflow数据集上实现了0.45的终点错误 (EPE),这是0.02的改进.
- 在KITTI 2015数据集的D1-all指标上,基本网络的表现优于5.6%.
结论:
- 拟议的AKC-Stereo网络通过整合自适应的内核卷曲和注意力机制,有效地增强了立体声匹配.
- 卡普和马尔模块显著改善了像素级别的表示和网络通用化.
- 这种方法在双眼立体相匹配精度方面取得了实质性的进步.
相关概念视频
01:20Deconvolution
132
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
132
01:17Convolution Properties II
173
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
173
01:11Residuals and Least-Squares Property
7.3K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.3K
01:26Linear Approximation in Frequency Domain
85
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
85
01:21Linear Approximation in Time Domain
64
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
64
01:20Convolution Properties I
137
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
137