Related papers: MaIR: A Locality- and Continuity-Preserving Mamba …

Radar-camera depth estimation must turn an ultra-sparse, all-weather, metric radar signal into a dense per-pixel depth map. Existing methods -- concatenation, confidence-aware gating, sparse supervision, graph-based extraction -- combine…

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision. Selective SSMs are viewed as dual models, in…

The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the…

Hyperspectral image (HSI) classification constitutes the fundamental research in remote sensing fields. Convolutional Neural Networks (CNNs) and Transformers have demonstrated impressive capability in capturing spectral-spatial contextual…

In the coded aperture snapshot spectral imaging system, Deep Unfolding Networks (DUNs) have made impressive progress in recovering 3D hyperspectral images (HSIs) from a single 2D measurement. However, the inherent nonlinear and ill-posed…

Despite decades of progress, a truly input-size agnostic visual encoder-a fundamental characteristic of human vision-has remained elusive. We address this limitation by proposing \textbf{MambaEye}, a novel, causal sequential encoder that…

State-Space Models (SSMs) have emerged as an efficient alternative to transformers, yet existing visual SSMs retain deeply ingrained biases from their origins in natural language processing. In this paper, we address these limitations by…

Convolutional neural networks and Transformer have made significant progresses in multi-modality medical image super-resolution. However, these methods either have a fixed receptive field for local learning or significant computational…

Computational pathology (CPath) has significantly advanced the clinical practice of pathology. Despite the progress made, Multiple Instance Learning (MIL), a promising paradigm within CPath, continues to face challenges, particularly…

Accelerated MRI reconstruction requires recovering missing details while preserving anatomically coherent structures across large spatial regions. State-space models such as Mamba provide efficient long-range modeling, making them…

We propose an innovative enhancement to the Mamba framework by increasing the Hausdorff dimension of its scanning pattern through a novel Hilbert Selective Scan mechanism. This mechanism explores the feature space more effectively,…

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods…

In computational pathology, extracting spatial features from gigapixel whole slide images (WSIs) is a fundamental task, but due to their large size, WSIs are typically segmented into smaller tiles. A critical aspect of this analysis is…

Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by…

Although Mamba models greatly improve Hyperspectral Image (HSI) classification, they have critical challenges in terms defining efficient and adaptive token sequences for improve performance. This paper therefore presents CSSMamba…

Small lesions play a critical role in early disease diagnosis and intervention of severe infections. Popular models often face challenges in segmenting small lesions, as it occupies only a minor portion of an image, while down\_sampling…

Accurate medical image segmentation is an integral part of the medical image analysis pipeline that requires the ability to merge local and global information. While vision transformers are able to capture global interactions using vanilla…

Video super-resolution remains a major challenge in low-level vision tasks. To date, CNN- and Transformer-based methods have delivered impressive results. However, CNNs are limited by local receptive fields, while Transformers struggle with…

Two-view correspondence learning aims to discern true and false correspondences between image pairs by recognizing their underlying different information. Previous methods either treat the information equally or require the explicit storage…