The metaverse, a revolutionary concept shaping the future of the Internet, has aroused concern and discussion among governments, the business sector, and ordinary netizens. While there is abundant literature on virtual worlds, academic study on the “metaverse” is scarce. Therefore, by analyzing the development of U.S. metaverse, we found that its evolution can be roughly divided into three major stages. Deep corporate engagement, a cutting-edge research and technology system, and the industrial chain all contribute significantly to the growth of metaverse in the United States. In order to take advantage of the chance to develop the metaverse, China can learn a lot from the United States. In terms of the established standard system, data security and privacy protection, and the development path, we examine the challenges associated with the development of China’s metaverse. On the basis of this, practical suggestions are made for the development of the Chinese metaverse.

Recent self-supervised learning (SSL) methods have demonstrated impressive results in learning visual representations from unlabeled remote sensing (RS) images. However, most RS images predominantly consist of scenographic scenes containing multiple ground objects without explicit foreground targets, which limits the performance of existing SSL methods that focus on foreground targets. This raises the question: Is there a method that can automatically aggregate similar objects within scenographic RS images, thereby enabling models to differentiate knowledge embedded in various geospatial patterns for improved feature representation? In this work, we present the pattern integration and enhancement vision transformer (PIEViT), a novel SSL framework designed specifically for RS imagery. PIEViT utilizes a teacher-student architecture to address both image-level and patch-level tasks. It employs a proposed, geospatial pattern cohesion (GPC) module to explore the natural clustering of patches, enhancing the differentiation of individual features. A feature integration projection (FIP) module is employed to further refine masked token reconstruction using geospatially clustered patches. We validated PIEViT across multiple downstream tasks, including object detection, semantic segmentation, and change detection. Experiments demonstrated that PIEViT enhances the representation of internal patch features, providing significant improvements over existing self-supervised baselines. It achieves excellent results in object detection, land cover classification, and change detection, underscoring its robustness, generalization, and transferability for RS image interpretation tasks.

Recent pan-sharpening methods have predominantly utilized techniques tailored for natural image scenes, often overlooking the unique features arising from non-overlapping spectral responses. In light of this, we have reevaluated the utility of panchromatic (PAN) images and introduced a theory anchored in the spectral response of satellite sensors. This posits that a PAN image is effectively a linear weighted summation of individual bands from its corresponding multi-spectral (MS) image, offset by an error map. We developed a deep unmixing network termed “DUN” that integrates an unmixing network, a fusion mechanism, and a distinctive mutual information contrastive loss function. Notably, the unmixing network is adept at decomposing a PAN image into its MS counterpart and error map. Further, the demixed image alongside the low-resolution MS image is channeled into the fusion network for pan-sharpening. Recognizing the challenges of achieving robust supervised learning directly from the unmixing phase, we have innovated a mutual information contrastive learning loss function, ensuring enhanced separation and minimizing overlap during the unmixing process. Preliminary experiments underscore both the quantitative and qualitative prowess of the proposed method.

In the realm of remote sensing change detection, deep learning-based pixel-level methods have shown commendable accuracy and speed. However, due to the difficulty in distinguishing between each changed object and the high matching accuracy required, there are still limitations in practical applications. To address these issues, we propose Change DINO, a novel unified object-level change detection and segmentation framework and the inaugural Transformer-based object-level change detection framework, which leverages the Hierarchical Temporal Fusion Module (HTFM) with dual branches to extract change features from bi-temporal images, integrating these features into the Transformer's encoder-decoder and segmentation branches. Experimental results show that compared to other pixel-level (including Transformer-based) change detection methods, Change DINO exhibits superior performance even on pixel-level evaluation strategy, achieving F1 score improvements of 5.09% and 10.31% compared with Transformer-based methods. This capability significantly mitigates the limitations inherent in pixel-level detection, showcasing Change DINO's substantial potential for diverse applications in change detection tasks.

In remote sensing image change detection (CD), leveraging distant contextual information is crucial for accuracy. Traditional neural network training, which involves image cropping, limits the perception of such information in large-scale images. To overcome this, we propose the "Panoramic Change Analysis Framework (PCA-F)" for high-resolution remote sensing CD. This innovative framework features a dual-branch architecture to integrate broad area information and uses advanced spatial alignment for merging wide-area and local features. PCA-F overcomes traditional method limitations and integrates well with various CD networks. The experimental results demonstrate a significant improvement in accuracy for the three baseline methods on two datasets (BIT: 3.51%, 4.66%; Changeformer: 1.49%, 2.64%; RDPNet: 1.97%, 5.31%), offering a new direction for enhancing CD performance in remote sensing imagery.

The phenomenon of nonoverlapping spectral responses is an inevitable but an overlooked problem in the deep-learning-based panchromatic (PAN) and multispectral (MS) images’ fusion task, which will introduce some error information from the PAN image. In light of this, we construct a novel prior model based on spectral response theory and develop a model-based pan-sharpening network. Specifically, we extract the initial error map from the PAN and interpolate the MS image as the initial pan-sharpened result. Then, two optimization problems regularized by the deep prior are formulated to update the error map and pan-sharpened image. By alternately optimizing the above subtasks, error information is gradually separated from PAN images and the lost texture information in MS images is gradually restored, which can effectively alleviate the negative impact of low coupling information from PAN and MS images. Plenty of experimental results on different kinds of satellite datasets demonstrate that the proposed method shows a better balance between interpretability and lightweight structure. The proposed method will be open-sourced inhttps://github.com/jiaming-wang/DERN.

Recognition and localization models can be generally decomposed into three components: encoder, decoder, and task head. In this paper, we rethink the necessity of decoder, as we observe that it brings additional computational and parametric burden. We thus propose to remove the decoder and present a bidirectional cross-scale architecture that is able to obtain rich semantic information and precise localization in a unified backbone. Extensive experiments demonstrate that, different from common encoder-decoder models and other down-sampling and up-sampling backbones, the proposed BiCSNet achieves improved performances compared to existing architectures for pixel-level tasks. In object detection, our BiCSNet brings significant performance improvement by ~ 3% AP at various scales with 13% – 23% fewer FLOPS, compared with ResNet-FPN models on COCO dataset. In Instance segmentation, the AP can be improved by 1% over SpineNet. BiCSNet is also promising for semantic segmentation tasks, as the proposed BiCSNet pre-trained on ImageNet alone significantly outperforms DeepLabv3 pre-trained on both ImageNet and COCO dataset by 1.3% in mIOU with 89% fewer FLOPs on PASCAL VOC 2012.

Most existing deep learning-based pan-sharpening methods own several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement. To address these challenges in pan-sharpening, we propose a novel dual-path fusion network (DPFN). The proposed DPFN includes two major components: 1) the global subnetwork (GSN) and 2) the local subnetwork (LSN). In particular, GSN aims to search similar image blocks in panchromatic (PAN) space and multispectral (MS) space and exploits HR textural information from the PAN space and spectral information from the MS space for the fine representation of pan-sharpened MS features by employing a cross nonlocal block. Meanwhile, the proposed LSN based on a high-pass modification block (HMB) is designed to learn the high-pass information, aiming to enhance bandwise spatial information from MS images. HMB forces the fused image to obtain high-frequency details from PAN images. Moreover, to facilitate the generation of visually appealing pan-sharpened images, we propose a perceptual loss function and further optimize the model based on high-level features in the near-infrared space. Experiments demonstrate the superior performance of the proposed method quantitatively and qualitatively compared to existing state-of-the-art pan-sharpening methods. The source code is available athttps://github.com/jiaming-wang/DPFN.

The goal of pan-sharpening tasks is to fuse panchromatic (PAN) images and low-spatial-resolution (LR) multispectral (MS) images for the purpose of aggregating texture and spectral information. Although traditional embedding-based pan-sharpening methods achieve competitive results, they are limited by the shallow network and not suitable for large-scale datasets. In this study, we design a novel multiscale locally linear embedding residual network (LLERN) that consists of two phases: the spectral preservation phase and the structural preservation phase. As the pretreatment of the structural preservation network, the spectral preservation network aims to upscale the LR MS image while retaining spectral information. The proposed locally linear embedding residual block (LLERB) in the structural preservation phase can search for similar sparse patches from the PAN image space and embed the corresponding local geometric relationship into the residual space to enhance the MS image. Extensive experiments suggest that the proposed LLERN outperforms state-of-the-art methods from visual and quantitative perspectives, and confirm the assumption that LR image patches and residual image patches in a local region share a similar manifold structure, which can be used to guide deep-learning modeling with improved interpretability. The source code is available athttps://github.com/jiaming-wang/LLERN.

Deep-learning-based super-resolution methods have been extensively studied and achieved significant performance with deep convolutional neural networks. However, the results still suffer from the ringing effect, especially in satellite image super-resolution tasks, due to the loss of image details in the satellite degradation process. In this paper, we build a novel satellite super-resolution framework by decomposing a high-resolution image into three components, i.e., low-resolution, artifact, and high-frequency information. Specifically, we propose an artifact removal network with a self-adaption difference convolution (SDC) to fully exploit the structure prior in the low-resolution image and predict the artifact map. Considering that the artifact map and the high-frequency map share a similar pattern, we introduce the supervised structure correction block (SSC) that establishes a bridge between the high-frequency generation process and the artifact removal process. Experimental results on satellite images demonstrate that the proposed method owns an improved tradeoff between the performance and the computational cost compared to existing state-of-the-art satellite and natural super-resolution methods. The source code is available at https://github.com/jiaming-wang/ARSRN.

Most existing deep learning-based pan-sharpening methods have several widely recognized issues, such as spectral distortion and insufficient spatial texture enhancement, we propose a novel pan-sharpening convolutional neural network based on a high-pass modification b lock. Different from existing methods, the proposed block is designed to learn the high-pass information, leading to enhance spatial information in each band of the multi-spectral-resolution images. To facilitate the generation of visually appealing pan-sharpened images, we propose a perceptual loss function and further optimize the model based on high-level features in the near-infrared space. Experiments demonstrate the superior performance of the proposed method compared to the state-of the-art pan-sharpening methods, both quantitatively and qualitatively. The proposed model is open-sourced at https://github.com/jiaming-wang/HMB.

Recently, satellites with high temporal resolution have fostered wide attention in various practical applications. Due to limitations of bandwidth and hardware cost, however, the spatial resolution of such satellites is considerably low, largely limiting their potentials in scenarios that require spatially explicit information. To improve image resolution, numerous approaches based on training low-high resolution pairs have been proposed to address the super-resolution (SR) task. De-spite their success, however, low/high spatial resolution pairs are usually difficult to obtain in satellites with a high temporal resolution, making such approaches in SR impractical to use. In this paper, we proposed a new unsupervised learning framework, called "MIP", which achieves SR tasks without low/high resolution image pairs. First, random noise maps are fed into a designed generative adversarial network (GAN) for reconstruction. Then, the proposed method converts the reference image to latent space as the migration image prior. Finally, we update the input noise via an implicit method, and further transfer the texture and structured information from the reference image. Extensive experimental results on the Draper dataset show that MIP achieves significant improvements over state-of-the-art methods both quantitatively and qualitatively. The proposed MIP is open-sourced at https://github.com/jiaming-wang/MIP.