Recently, global SfM has been attracting many researchers, mainly because of its time efficiency. Most of these methods are based on averaging relative orientations (ROs). Therefore, eliminating incorrect ROs is of great significance for improving the robustness of global SfM. In this paper, we propose a method to eliminate wrong ROs which have resulted from repetitive structure (RS) and very short baselines (VSB). We suggest two corresponding criteria that indicate the quality of ROs. These criteria are functions of potentially conjugate points resulting from local image matching of image pairs, followed by a geometry check using the 5-point algorithm combined with RANSAC. RS is detected based on counts of corresponding conjugate points of the various pairs, while VSB is found by inspecting the intersection angles of corresponding image rays. Based on these two criteria, incorrect ROs are eliminated. We demonstrate the proposed method on various datasets by inserting our refined ROs into a global SfM pipeline. The experiments show that compared to other methods we can generate the better results in this way.

No abstract

No abstract

Structure from motion (SfM) has been treated as a mature technique to carry out the task of image orientation and 3D reconstruction. However, it is an ongoing challenge to obtain correct reconstruction results from image sets consisting of problematic match pairs. This paper investigated two types of problematic match pairs, stemming from repetitive structures and very short baselines. We built a weighted view-graph based on all potential match pairs and propose a progressive SfM method (PRMP-PSfM) that iteratively prioritizes and refines its match pairs (or edges). The method has two main steps: initialization and expansion. Initialization is developed for reliable seed reconstruction. Specifically, we prioritize a subset of match pairs by the union of multiple independent minimum spanning trees and refine them by the idea of cycle consistency inference (CCI), which aims to infer incorrect edges by analyzing the geometric consistency over cycles of the view-graph. The seed reconstruction is progressively expanded by iteratively adding new minimum spanning trees and refining the corresponding match pairs, and the expansion terminates when a certain completeness of the block is achieved. Results from evaluations on several public datasets demonstrate that PRMP-PSfM can successfully accomplish the image orientation task for datasets with repetitive structures and very short baselines and can obtain better or similar accuracy of reconstruction results compared to several state-of-the-art incremental and hierarchical SfM methods.

Two psychophysical experiments were conducted to evaluate the performance of grayscale image colorization models, and to verify the objective image quality metrics adopted in grayscale image colorization. Twenty representative grayscale images were colourized by four colorization models and three typical metrics, root mean square error (RMSE), peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM), were used to characterize the objective quality of the colourized images. Forty observers were asked to evaluate those images based on their subjective preference in a pair‐comparison experiment, and to evaluate the perceived similarity between the generated and reference colour images using a seven‐point rating scale. The experimental results indicate that different colorization models and objective metrics exhibit different performance in different scenarios. Each colorization method has its own advantages and disadvantages while none of the tested models performed well for all images. For preference, the model proposed by Iizuka et al based on ImageNet performed better while for perceived similarity the models proposed by Zhang et al and Iizuka et al, also based on ImageNet, outperformed the models of Larsson et al and Iizuka et al which were based on the Places dataset. Due to the fact that many objects have instances of distinct colour, a colorization algorithm cannot correctly reconstruct ground truth image for most gray level images, although it was found that perceived similarity and preference ratings of observers were correlated. In addition, it was found that the tested objective metrics correlated poorly with the subjective judgments of the human observers and their performance varied significantly with image content. These findings demonstrate the limitations of current image colorization studies, and it is suggested that due consideration must be given to human visual perception when evaluating the performance of colorization models.