论文标题
从深直线上的鱼眼变形纠正
Fisheye Distortion Rectification from Deep Straight Lines
论文作者
论文摘要
本文提出了一个新型的线感矫正网络（LARECNET），以根据经典观察结果解决Fisheye失真整流的问题，即3D空间中的直线仍应在图像平面中直接直线。具体而言，所提出的LARECNET包含三个顺序模块，以（1）从Fisheye图像中学习扭曲的直线； （2）从学习的热图和图像外观中估算失真参数； （3）通过提出的可区分整流层纠正输入图像。为了更好地训练和评估所提出的模型，我们创建了一个富含合成线的Fisheye（SLF）数据集，其中包含失真参数和畅通无阻的鱼眼图像的扭曲直线。提出的方法使我们能够同时校准几何变形参数并纠正鱼眼图像。广泛的实验表明，我们的模型以几种评估指标的几何准确性和图像质量来实现最先进的性能。特别是，LARECNET纠正的图像在SLF数据集上达到了0.33像素的平均再投影误差，并产生最高的峰信噪比（PSNR）和结构相似性指数（SSIM）与地面图相比。
This paper presents a novel line-aware rectification network (LaRecNet) to address the problem of fisheye distortion rectification based on the classical observation that straight lines in 3D space should be still straight in image planes. Specifically, the proposed LaRecNet contains three sequential modules to (1) learn the distorted straight lines from fisheye images; (2) estimate the distortion parameters from the learned heatmaps and the image appearance; and (3) rectify the input images via a proposed differentiable rectification layer. To better train and evaluate the proposed model, we create a synthetic line-rich fisheye (SLF) dataset that contains the distortion parameters and well-annotated distorted straight lines of fisheye images. The proposed method enables us to simultaneously calibrate the geometric distortion parameters and rectify fisheye images. Extensive experiments demonstrate that our model achieves state-of-the-art performance in terms of both geometric accuracy and image quality on several evaluation metrics. In particular, the images rectified by LaRecNet achieve an average reprojection error of 0.33 pixels on the SLF dataset and produce the highest peak signal-to-noise ratio (PSNR) and structure similarity index (SSIM) compared with the groundtruth.
