Equivariant Graph Neural Networks (GNNs) have achieved remarkable success across diverse scientific applications. However, existing approaches face critical efficiency challenges when scaling to large geometric graphs and suffer significant performance degradation when the input graphs are sparsified for computational tractability. To address these limitations, we introduce FastEGNN and DistEGNN, two novel enhancements to equivariant GNNs for large-scale geometric graphs. FastEGNN employs a key innovation: a small ordered set of virtual nodes that effectively approximates the large unordered graph of real nodes. Specifically, we implement distinct message passing and aggregation mechanisms for different virtual nodes to ensure mutual distinctiveness, and minimize Maximum Mean Discrepancy (MMD) between virtual and real coordinates to achieve global distributedness. This design enables FastEGNN to maintain high accuracy while efficiently processing large-scale sparse graphs. For extremely large-scale geometric graphs, we present DistEGNN, a distributed extension where virtual nodes act as global bridges between subgraphs in different devices, maintaining consistency while dramatically reducing memory and computational overhead. We comprehensively evaluate our models across four challenging domains: N-body systems (100 nodes), protein dynamics (800 nodes), Water-3D (8,000 nodes), and our new Fluid113 K benchmark (113,000 nodes). Results demonstrate superior efficiency and performance, establishing new capabilities in large-scale equivariant graph learning.

Flexible endoscope motion tracking and analysis in mechanical simulators have proven useful for endoscopy training. Common motion tracking methods based on electromagnetic tracker are however limited by their high cost and material susceptibility. In this work, the motion-guided dual-camera vision tracker is proposed to provide robust and accurate tracking of the endoscope tip's 3D position. The tracker addresses several unique challenges of tracking flexible endoscope tip inside a dynamic, life-sized mechanical simulator. To address the appearance variation and keep dualcamera tracking consistency, the cross-camera mutual template strategy (CMT) is proposed by introducing dynamic transient mutual templates. To alleviate large occlusion and light-induced distortion, the Mamba-based motion-guided prediction head (MMH) is presented to aggregate historical motion with visual tracking. The proposed tracker achieves superior performance against state-of-the-art vision trackers, achieving 42% and 72% improvements against the second-best method in average error and maximum error. Further motion analysis involving novice and expert endoscopists also shows that the tip 3D motion provided by the proposed tracker enables more reliable motion analysis and more substantial differentiation between different expertise levels, compared with other trackers. Project page: https://github.com/PieceZhang/MotionDCTrack

Defocus blur is a persistent problem in microscope imaging that poses harm to pathology interpretation and medical intervention in cell microscopy and microscope surgery. To address this problem, a unified framework including the multi-pyramid transformer (MPT) and extended frequency contrastive regularization (EFCR) is proposed to tackle two outstanding challenges in microscopy deblur: longer attention span and data deficiency. The MPT employs an explicit pyramid structure at each net-work stage that integrates the cross-scale window attention (CSWA), the intra-scale channel attention (ISCA), and the feature-enhancing feed-forward network (FEFN) to capture long-range cross-scale spatial interaction and global channel context. The EFCR addresses the data de-ficiency problem by exploring latent deblur signals from different frequency bands. It also enables deblur knowl-edge transfer to learn cross-domain information from ex-tra data, improving deblur performance for labeled and unlabeled data. Extensive experiments and downstream task validation show the framework achieves state-of-the-art performance across multiple datasets. Project page: https:llgithub.comIPieceZhangIMPT-CataBlur.

Equivariant Graph Neural Networks (GNNs) have made remarkable success in a variety of scientific applications. However, existing equivariant GNNs encounter the efficiency issue for large geometric graphs and perform poorly if the input is reduced to sparse local graph for speed acceleration. In this paper, we propose FastEGNN, an enhanced model of equivariant GNNs on large geometric graphs. The central idea is leveraging a small ordered set of virtual nodes to approximate the large unordered graph of real nodes. In particular, we distinguish the message passing and aggregation for different virtual node to encourage the mutual distinctiveness, and minimize the Maximum Mean Discrepancy (MMD) between virtual and real coordinates to realize the global distributedness. FastEGNN meets all necessary E(3) symmetries, with certain universal expressivity assurance as well. Our experiments on N-body systems (100 nodes), proteins (800 nodes) and water-3D (8000 nodes), demonstrate that FastEGNN achieves a promising balance between accuracy and efficiency, and outperforms EGNN in accuracy even after dropping all edges in real systems like proteins and water-3D.

Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at https://github.com/cnyvfang/CORUN-Colabator.

Due to the inconsistent imaging environment, the styles of multitemporal multispectral images (MSIs) are quite different, such as image brightness and transparency. For multitemporal MSIs with different styles, the “same object with different spectra” problem is one of the biggest challenges in change detection. To overcome the challenge, a novel unsupervised spatial–spectral feature learning (FL) framework based on style transformation (ST) (called STFL-CD) is proposed for MSI change detection in this article. For dual-temporal MSIs, the proposed STFl-CD algorithm consists of two phases: ST and spatial–spectral FL. Since the image styles are inconsistent under different imaging environments, the first innovation is to transform the image styles through unmixing and reconstruction. Through ST, the challenge of the “same object with different spectra” problem will be reduced fundamentally. By introducing the attention mechanism, the other innovation is to extract the joint spectral–spatial change features based on a 3-D convolutional neural network with spatial and channel attention. In addition, for multitemporal MSIs, a multitemporal version STFL-CD (MT-STFL-CD) framework is designed based on a recurrent neural network to learn the correlation features between multitemporal remote sensing images. Both of the visual and quantitative results on the real MSI datasets indicate that the proposed unsupervised STFL-CD frameworks have significant advantages on multitemporal MSI change detection. In particular, the performance of the proposed unsupervised STFL-CD algorithm is even comparable to that of the state-of-the-art supervised or semisupervised methods.

Change detection (CD) for multispectral remote sensing images is an important approach to observe the changes of the earth. However, the same object usually has different spectra in multi-temporal images, which is one of the biggest challenges for CD. To overcome this problem, a novel unsupervised CD approach based on spectral transformation and joint spectral-spatial feature learning (STCD) is proposed for multispectral images in this paper. By exploring the relationship between imaging environment and the object spectra, the spectral transformation is used to suppress the phenomenon of “same object with different spectra”. Besides, a detection network with joint spectral-spatial feature learning is designed to extract the spectral-spatial features simultaneously to make the CD algorithm more robust. Both theoretical analyses and experiment results proved that the proposed STCD method is superior to the state-of-the-art unsupervised methods on multispectral images CD.