Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative models. However, most approaches are designed for specific tasks, restricting their generalizability to combine different types of condition. Developing a unified framework for image customization remains an open challenge. In this paper, we present DreamO, an image customization framework designed to support a wide range of tasks while facilitating seamless integration of multiple conditions. Specifically, DreamO utilizes a diffusion transformer (DiT) framework to uniformly process input of different types. During training, we introduce a feature routing constraint to facilitate the precise querying of relevant information from reference images. Additionally, we design a placeholder strategy that associates specific placeholders with conditions at particular positions, enabling control over the placement of conditions in the generated results. Moreover, we employ a progressive training strategy to ensure smooth model convergence and correct the generation quality of the final output. Extensive experiments demonstrate that the proposed DreamO can effectively perform various image customization tasks with high quality and flexibly integrate different types of control conditions. Project page: https://mc-e.github.io/project/DreamO

GaoFen1 is the first high-resolution earth observation satellite built in China, and carries four wide field-of-view (WFV) cameras to achieve large-scale monitoring and mapping. However, the unstable attitude measurement accuracy of the satellite generally imparts low geopositioning accuracy and inconsistent geometric error in overlapping areas of WFV images. A feasible and effective large-scale planar block adjustment (PBA) method is presented that corrects the geometric errors of the vast WFV images integrally, further improving the geometric accuracy of these images. In addition, whether ground control points (GCPs) are needed, and the effect of different numbers of GCPs on PBA accuracy is also investigated. Two key technologies are used in this paper. First, a universal PBA error equation based on the virtual control points is presented to allow PBA with or without GCPs. Second, an adjustment method aided by a digital elevation model is adopted to overcome the weak convergence geometry among WFV images, further ensuring stable estimation of PBA. The effectiveness of the proposed method was verified by 664 WFV images covering most of mainland China. The satisfactory experimental results indicate that the method presented herein is reasonable and effective, but that a certain number of GCPs is needed to ensure the accuracy of large-scale PBA results for WFV images.

Due to the all-weather and all-day advantage and the high geometric accuracy, the spaceborne synthetic aperture radar (SAR) stereo pair has a wide application in digital elevation model (DEM) production and ground control points (GCPs) extraction around the world. The GaoFen3 (GF3) remote sensing satellite is the first C-band multipolarization SAR satellite with a resolution of 1 m in China and plays an important role in commercial exploitation and scientific research. This letter performs a comprehensive analysis of the geometric accuracy for GF3 stereo pair orientation. By analyzing the orientation error sources, it is proven that the affine transformation model in image space can effectively compensate the unmodeled errors in GF3 imagery. Based on the rational polynomial coefficient model, the integrated orientation model for the GF3 stereo pair is presented here. Moreover, the model parameters and weight determination are further studied to analyze the influence of weight matrixes on geometric accuracy. Experimental results demonstrate that the proposed integrated orientation model can be effectively used for the GF3 stereo pair. The GCPs, convergent angle, and weight setting are the key factors influencing the geometric accuracy.

Image segmentation is the foundation of object-based image analysis, and many researchers have sought optimal segmentation results. The initial image oversegmentation and the optimal segmentation scale are two vital factors in high spatial resolution remote sensing image segmentation. With respect to these two issues, a novel image segmentation method combining superpixels with a minimum spanning tree is proposed in this paper. First, the image is oversegmented using a simple linear iterative clustering algorithm to obtain superpixels. Then, the superpixels are clustered by regionalization with a dynamically constrained agglomerative clustering and partitioning (REDCAP) algorithm using the initial number of segments, and the local variance (LV) and the rate of LV change (ROC-LV) indicator diagrams corresponding to the number of segments are obtained. The suitable number of image segments is determined according to the LV and ROC-LV indicator diagrams corresponding to the number of segments. Finally, the superpixels are reclustered using the REDCAP algorithm based on the suitable number of image segments to obtain the image segmentation result. Through two sets of experiments, the proposed method is compared with two other segmentation algorithms. The experimental results show that the proposed method outperforms the others and obtains good image segmentation results.

Many tools directly change programs, such as bug-fixing tools, program migration tools, etc. We call them program-modification tools. On the other hand, many programming languages use the C preprocessor, such as C, C++, and Objective-C. Because of the complexity of preprocessors, many program-modification tools either fail to produce sound results under the presence of preprocessor directives, or give up completely and deal only with preprocessed code.

The correlation between test coverage and test effectiveness is important to justify the use of coverage in practice. Existing results on imperative programs mostly show that test coverage predicates effectiveness. However, since functional programs are usually structurally different from imperative ones, it is unclear whether the same result may be derived and coverage can be used as a prediction of effectiveness on functional programs. In this paper we report the first empirical study on the correlation between test coverage and test effectiveness on functional programs. We consider four types of coverage: as input coverages, statement/branch coverage and expression coverage, and as oracle coverages, count of assertions and checked coverage. We also consider two types of effectiveness: raw effectiveness and normalized effectiveness. Our results are twofold. (1) In general the findings on imperative programs still hold on functional programs, warranting the use of coverage in practice. (2) On specific coverage criteria, the results may be unexpected or different from the imperative ones, calling for further studies on functional programs.

This poster presents a tree-based online presentation strategy and its implementation. In this strategy, instructors and students can interactively add sub-branches on the Web-based presentations, either for extending a sub-topic or to raise questions under a specific slide. A hierarchical visualisation method is provided to support the recursive interactions of branch expanding and tree browsing.