基于自监督学习的单目图像深度估计
Self-Supervised Learning based Depth Estimation from Monocular Images
AI总结：
本文探索在自监督单目深度估计中引入姿态估计、高效亚像素卷积插值和语义分割等技术，并去除相机内参、加入天气增强，以提升深度图的细粒度与全局一致性。
摘要：
深度估计在计算机视觉领域具有广泛的应用，例如目标跟踪、增强现实和自动驾驶汽车。单目深度估计的目标是，给定一幅二维单目 RGB 图像作为输入，预测其深度图。传统的深度估计方法基于深度线索，并使用诸如对极几何等概念。随着卷积神经网络的发展，深度估计取得了巨大进步。在本项目中，我们的目标是探索对现有最先进的基于深度学习的深度估计模型进行可能的扩展，并考察性能指标是否可以进一步提升。从更广泛的意义上说，我们正在研究实现姿态估计、高效亚像素卷积插值和语义分割估计技术的可能性，以进一步增强我们所提出的架构，并提供更细粒度且更具全局一致性的深度图预测。我们还计划在训练过程中去除相机内参，并应用天气增强来进一步泛化我们的模型。
英文摘要：
Depth Estimation has wide reaching applications in the field of Computer vision such as target tracking, augmented reality, and self-driving cars. The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB image as input. The traditional depth estimation methods are based on depth cues and used concepts like epipolar geometry. With the evolution of Convolutional Neural Networks, depth estimation has undergone tremendous strides. In this project, our aim is to explore possible extensions to existing SoTA Deep Learning based Depth Estimation Models and to see whether performance metrics could be further improved. In a broader sense, we are looking at the possibility of implementing Pose Estimation, Efficient Sub-Pixel Convolution Interpolation, Semantic Segmentation Estimation techniques to further enhance our proposed architecture and to provide fine-grained and more globally coherent depth map predictions. We also plan to do away with camera intrinsic parameters during training and apply weather augmentations to further generalize our model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
