Abstract:In this work, we propose a novel approach to prioritize the depth map computation of multi-view stereo (MVS) to obtain compact 3D point clouds of high quality and completeness at low computational cost. Our prioritization approach operates before the MVS algorithm is executed and consists of two steps. In the first step, we aim to find a good set of matching partners for each view. In the second step, we rank the resulting view clusters (i.e. key views with matching partners) according to their impact on the f… Show more
“…However, these methods usually require complex computation for high-quality depth map estimation. To expand the reconstruction scale to a larger extent at a lower computational cost, Xue et al [31] proposed a novel multi-view 3D dense matching method for large-scale aerial images using a divide-and-conquer scheme, and Mostegel et al [32] innovatively proposed to prioritize the depth map computation of MVS by confidence prediction to efficiently obtain compact 3D point clouds with high quality and completeness. Wei et al [33] proposed a novel selective joint bilateral upsampling and depth propagation strategy for high-resolution unstructured MVS.…”
Section: Depth-map Merging Based Methodsmentioning
This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structures, especially for linear objects. Our framework begins with a sparse reconstruction carried out by an incremental Structure-from-Motion. Based on the reconstructed sparse map, a novel detail preserving PatchMatch approach is applied for depth estimation of each image view. The estimated depth maps of multiple views are then fused to a dense point cloud in a memory-efficient way, followed by a detail-aware surface meshing method to extract the final surface mesh of the captured scene. Experiments on ETH3D benchmark show that the proposed method outperforms other state-of-the-art methods on F1-score, with the running time more than 4 times faster. More experiments on large-scale photo collections demonstrate the effectiveness of the proposed framework for large-scale scene reconstruction in terms of accuracy, completeness, memory saving, and time efficiency.
“…However, these methods usually require complex computation for high-quality depth map estimation. To expand the reconstruction scale to a larger extent at a lower computational cost, Xue et al [31] proposed a novel multi-view 3D dense matching method for large-scale aerial images using a divide-and-conquer scheme, and Mostegel et al [32] innovatively proposed to prioritize the depth map computation of MVS by confidence prediction to efficiently obtain compact 3D point clouds with high quality and completeness. Wei et al [33] proposed a novel selective joint bilateral upsampling and depth propagation strategy for high-resolution unstructured MVS.…”
Section: Depth-map Merging Based Methodsmentioning
This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structures, especially for linear objects. Our framework begins with a sparse reconstruction carried out by an incremental Structure-from-Motion. Based on the reconstructed sparse map, a novel detail preserving PatchMatch approach is applied for depth estimation of each image view. The estimated depth maps of multiple views are then fused to a dense point cloud in a memory-efficient way, followed by a detail-aware surface meshing method to extract the final surface mesh of the captured scene. Experiments on ETH3D benchmark show that the proposed method outperforms other state-of-the-art methods on F1-score, with the running time more than 4 times faster. More experiments on large-scale photo collections demonstrate the effectiveness of the proposed framework for large-scale scene reconstruction in terms of accuracy, completeness, memory saving, and time efficiency.
“…At the same time, they suffer from noise and artifacts, especially from reflective or transparent surfaces. In addition, depth information can also be obtained from depth defocus [4] [5], multi-view Stereo (MVS) [6] [7], and obtained structure from motion (SFM) [8]. However, these methods are either timeconsuming or have low depth accuracy.…”
Depth information is very important for machines to perceive the environment and estimate their own state. Significant advances in robotics engineering and self-driving cars in recent decades have increased the demand for accurate depth measurements. Traditional depth estimation methods include motion structure and stereo vision matching, but these are based on the feature correspondence of multiple viewpoints, and at the same time, the predicted depth map is sparse. Depth estimation is a traditional task in computer vision that can be properly predicted by applying a variety of procedures, whereas inferring depth information from a single image is an ill-posed problem. The main objective of this paper is to provide a brief overview of the development of monocular depth estimation techniques based on deep learning. This article attempts to give an overview of supervised, unsupervised, and datasets and evaluation metrics. We conclude with a brief analysis of future developments.
“…In MVS, images must satisfy quality criteria [6] to obtain high-quality models. These criteria may slightly vary in different MVS algorithms, but there are some standard criteria such as the coverage/visibility, resolution, incidence angle, baseline, and parallax [7][8][9]. When a 3D model of the surveyed structure is available (i.e., 3D Computer-aided Design (CAD), building information modeling (BIM), 2.5D digital elevation model, rough photometric reconstruction), the UAV's camera views/paths can be designed in a model-based fashion where the optimal trajectories can be computed by maximizing the MVS quality at each observed surface of the 3D structures [10].…”
This paper introduces a new UAV path planning method for creating high-quality 3D reconstruction models of large and complex structures. The core of the new method is incorporating the topology information of the surveyed 3D structure to decompose the multi-view stereo path planning into a collection of overlapped view optimization problems that can be processed in parallel. Different from the existing state-of-the-arts that recursively select the vantage camera views, the new method iteratively resamples all nearby cameras (i.e., positions/orientations) together and achieves a substantial reduction in computation cost while improving reconstruction quality. The new approach also provides a higher-level automation function that facilitates field implementations by eliminating the need for redundant camera initialization as in existing studies. Validations are provided by measuring the variance between the reconstructions to the ground truth models. Results from three synthetic case studies and one real-world application are presented to demonstrate the improved performance. The new method is expected to be instrumental in expanding the adoption of UAV-based multi-view stereo 3D reconstruction of large and complex structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.