In this paper, we propose a depth-map merging based multiple view stereo method for large-scale scenes which takes both accuracy and efficiency into account. In the proposed method, an efficient patch-based stereo matching process is used to generate depth-map at each image with acceptable errors, followed by a depth-map refinement process to enforce consistency over neighboring views. Compared to state-of-the-art methods, the proposed method can reconstruct quite accurate and dense point clouds with high computational efficiency. Besides, the proposed method could be easily parallelized at image level, i.e., each depth-map is computed individually, which makes it suitable for large-scale scene reconstruction with high resolution images. The accuracy and efficiency of the proposed method are evaluated quantitatively on benchmark data and qualitatively on large data sets.

Depth completion aims to recover pixelwise depth from incomplete and noisy depth measurements with or without the guidance of a reference RGB image. This task attracted considerable research interest due to its importance in various computer vision-based applications, such as scene understanding, autonomous driving, 3-D reconstruction, object detection, pose estimation, trajectory prediction, and so on. As the system input, an incomplete depth map is usually generated by projecting the 3-D points collected by ranging sensors, such as LiDAR in outdoor environments, or obtained directly from RGB-D cameras in indoor areas. However, even if a high-end LiDAR is employed, the obtained depth maps are still very sparse and noisy, especially in the regions near the object boundaries, which makes the depth completion task a challenging problem. To address this issue, a few years ago, conventional image processing-based techniques were employed to fill the holes and remove the noise from the relatively dense depth maps obtained by RGB-D cameras, while deep learning-based methods have recently become increasingly popular and inspiring results have been achieved, especially for the challenging situation of LiDAR-image-based depth completion. This article systematically reviews and summarizes the works related to the topic of depth completion in terms of input modalities, data fusion strategies, loss functions, and experimental settings, especially for the key techniques proposed in deep learning-based multiple input methods. On this basis, we conclude by presenting the current status of depth completion and discussing several prospects for its future research directions.

As an intermediate step between raw remote sensing data and digital maps, remote sensing data classification has been a challenging and long-standing problem in the remote sensing research community. In this work, an automated and effective supervised classification framework is presented for classifying high-resolution remote sensing data. Specifically, the presented method proceeds in three main stages: feature extraction, classification, and classified result refinement. In the feature extraction stage, both multispectral images and 3D geometry data are used, which utilizes the complementary information from multisource data. In the classification stage, to tackle the problems associated with too many training samples and take full advantage of the information in the large-scale dataset, a random forest (RF) ensemble learning strategy is proposed by combining several RF classifiers together. Finally, an improved fully connected conditional random field (FCCRF) graph model is employed to derive the contextual information to refine the classification results. Experiments on the ISPRS Semantic Labeling Contest dataset show that the presented 3-stage method achieves 86.9% overall accuracy, which is a new state-of-the-art non-CNN (convolutional neural networks)-based classification method.

Urban scene modeling is a challenging task for the photogrammetry and computer vision community due to its large scale, structural complexity, and topological delicacy. This paper presents an efficient multistep modeling framework for large-scale urban scenes from aerial images. It takes aerial images and a textured 3D mesh model generated by an image-based modeling system as the input and outputs compact polygon models with semantics at different levels of detail (LODs). Based on the key observation that urban buildings usually have piecewise planar rooftops and vertical walls, we propose a segment-based modeling method, which consists of three major stages: scene segmentation, roof contour extraction, and building modeling. By combining the deep neural network predictions with geometric constraints of the 3D mesh, the scene is first segmented into three classes. Then, for each building mesh, the 2D line segments are detected and used to slice the ground into polygon cells, followed by assigning each cell a roof plane via a MRF optimization. Finally, the LOD model is obtained by extruding cells to their corresponding planes. Compared with direct modeling in 3D space, we transform the mesh into a uniform 2D image grid representation and most of the modeling work is performed in 2D space, which has the advantages of low computational complexity and high robustness. In addition, our method doesn't require any global prior, such as the Manhattan or Atlanta world assumption, making it flexible to model scenes with different characteristics and complexity. Experiments on both single buildings and large-scale urban scenes demonstrate that by combining 2D photometric with 3D geometric information, the proposed algorithm is robust and efficient in urban scene LOD vectorized modeling compared with the state-of-the-art approaches.

Image based modeling and laser scanning are two commonly used approaches in large-scale architectural scene reconstruction nowadays. In order to generate a complete scene reconstruction, an effective way is to completely cover the scene using ground and aerial images, supplemented by laser scanning on certain regions with low textures and complicated structures. Thus, the key issue is to accurately calibrate cameras and register laser scans in a unified framework. To this end, we proposed a three-step pipeline for complete scene reconstruction by merging images and laser scans. First, images are captured around the architecture in a multi-view and multi-scale way and are feed into a structure-from-motion (SfM) pipeline to generate SfM points. Then, based on the SfM result, the laser scanning locations are automatically planned by considering textural richness, structural complexity of the scene and spatial layout of the laser scans. Finally, the images and laser scans are accurately merged in a coarse-to-fine manner. Experimental evaluations on two ancient Chinese architecture datasets demonstrate the effectiveness of our proposed complete scene reconstruction pipeline.

In this paper, we put forward a new method for surface reconstruction from image-based point clouds. In particular, we introduce a new visibility model for each line of sight to preserve scene details without decreasing the noise filtering ability. To make the proposed method suitable for point clouds with heavy noise, we introduce a new likelihood energy term to the total energy of the binary labeling problem of Delaunay tetrahedra, and we give its s-t graph implementation. Besides, we further improve the performance of the proposed method with the dense visibility technique, which helps to keep the object edge sharp. The experimental result shows that the proposed method rivalled the state-of-the-art methods in terms of accuracy and completeness, and performed better with reference to detail preservation.