Recently, generative foundation models have significantly advanced large-scale text-driven natural image generation and have become a prominent research trend across various vertical domains. However, in the remote se...
详细信息
Recently, generative foundation models have significantly advanced large-scale text-driven natural image generation and have become a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on large-scale text-to-image (text2image) generation technology. Existing remote sensing image-text datasets are small in scale and confined to specific geographic areas and scene types. Besides, existing text2image methods have struggled to achieve global-scale, multi-resolution controllable, and unbounded image generation. To address these challenges, this paper presents two key contributions: the Git-10M dataset and the Text2Earth foundation model. Git-10M is a global-scale image-text dataset comprising 10.5 million image-text pairs, 5 times larger than the previous largest one. The dataset contains essential resolution information and covers a wide range of geographic scenes and contains essential geospatial metadata, significantly surpassing existing datasets in both size and diversity. Building on Git-10M, we propose Text2Earth, a 1.3 billion parameter generative foundation model based on the diffusion framework to model global-scale remote sensing scenes. Text2Earth integrates a resolution guidance mechanism, enabling users to specify image resolutions. A dynamic condition adaptation strategy is proposed for training and inference to improve image generation quality. Text2Earth not only excels in zero-shot text2image generation but also demonstrates robust generalization and flexibility across multiple tasks, including unbounded scene construction, image editing, and cross-modal image generation. This robust capability surpasses previous models restricted to the basic fixed size and limited scene types. On the previous text2image benchmark dataset, Text2Earth outperfoms previous models with a significant improvement of +26.23 FID and +20.95% Zero-shot Cls-OA metric. Our project page is https://chen-y
Warfare simulation Environment for Army Weapon and Equipment systems (WSAWES) provide a tactically robust environment for simulation experiments. The science and technology on complex Land systemssimulation Laborator...
详细信息
Aiming at improving the target positioning accuracy, the formation configuration of anti-radiation loitering munitions is optimized. Firstly the time difference measuring error and positioning error of the loitering m...
详细信息
The suspension system with high performances is an important factor ensuring the tracked vehicle mobility and comfortable in different situations. Magneto rheological dampers, which are semi-active suspension equipmen...
详细信息
This study investigates the scheduling problem ofmultiple agile optical satelliteswith large-scale *** problem is difficult to solve owing to the time-dependent characteristic of agile optical satellites,complex const...
详细信息
This study investigates the scheduling problem ofmultiple agile optical satelliteswith large-scale *** problem is difficult to solve owing to the time-dependent characteristic of agile optical satellites,complex constraints,and considerable solution *** solve the problem,we propose a scheduling method based on an improved sine and cosine algorithm and a task merging *** first establish a scheduling model with task merging constraints and observation action constraints to describe the ***,an improved sine and cosine algorithm is proposed to search for the optimal solution with the maximum profit *** adaptive cosine factor and an adaptive greedy factor are adopted to improve the ***,a taskmerging method with a task reallocation mechanism is developed to improve the scheduling *** results demonstrate the superiority of the proposed algorithm over the comparison algorithms.
We generalize the concept of homomorphisms between Hilbert C∗-modules to the concept of Jordan homomorphisms. Let M be a Hilbert C∗-module over a C∗-algebra A and φ:M→M be a map. Under the condition that A is commut...
详细信息
Event-triggered control has attracted considerable attention for its effectiveness in resource-restricted applications. To make event-triggered control as an end-to-end solution, a key issue is how to effectively lear...
详细信息
Combining the linear canonical transform and the Riesz transform, we introduce the linear canonical Riesz transform (for short, LCRT), which is further proved to be a linear canonical multiplier. Using this LCRT multi...
Aiming at improving the target positioning accuracy,the formation configuration of anti-radiation loitering munitions is *** the time difference measuring error and positioning error of the loitering munitions are ana...
详细信息
ISBN:
(纸本)9781479970186
Aiming at improving the target positioning accuracy,the formation configuration of anti-radiation loitering munitions is *** the time difference measuring error and positioning error of the loitering munitions are analyzed and the error propagation model is *** the formation configuration design model is established based on the proposed time difference localization algorithm and the formation flying boundary ***,considering the nonlinear features of optimization function for configuration optimization design,the genetic algorithm is introduced to obtain the optimal *** simulation results show that,compared with the traditional formation configurations,the optimization design of configuration can acquire higher estimation accuracy of target ***,the designed configuration has strong *** accuracy estimations of target position can be obtained under a wide range of target position changes.
This paper systematically investigates the performance of the consensus-based distributed filter under misspecified noise covariances. First, we introduce four quantities: the nominal filter parameter, the nominal est...
详细信息
暂无评论