Related papers: MBMamba: When Memory Buffer Meets Mamba for Struct…

In the field of biomedical image analysis, the quest for architectures capable of effectively capturing long-range dependencies is paramount, especially when dealing with 3D image segmentation, classification, and landmark detection.…

In this paper, we consider the problem in defocus image deblurring. Previous classical methods follow two-steps approaches, i.e., first defocus map estimation and then the non-blind deblurring. In the era of deep learning, some researchers…

Translating NIR to the visible spectrum is challenging due to cross-domain complexities. Current models struggle to balance a broad receptive field with computational efficiency, limiting practical use. Although the Selective Structured…

Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D…

Recent advancements in the Mamba architecture, with its linear computational complexity, being a promising alternative to transformer architectures suffering from quadratic complexity. While existing works primarily focus on adapting Mamba…

We propose Factorization Memory, an efficient recurrent neural network (RNN) architecture that achieves performance comparable to Transformer models on short-context language modeling tasks while also demonstrating superior generalization…

Image deblurring is a notoriously challenging ill-posed inverse problem. In recent years, a wide variety of approaches have been proposed based upon regularization at the level of the image or on techniques from machine learning. We propose…

Diffusion Models have become very popular for Semantic Image Synthesis (SIS) of human faces. Nevertheless, their training and inference is computationally expensive and their computational requirements are high due to the quadratic…

The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency. However, the inherent causal modeling limitation of Mamba, where each token depends…

Quad Bayer demosaicing is the central challenge for enabling the widespread application of Hybrid Event-based Vision Sensors (HybridEVS). Although existing learning-based methods that leverage long-range dependency modeling have achieved…

Mamba has attracted widespread interest as a general-purpose sequence model due to its low computational complexity and competitive performance relative to transformers. However, its performance can degrade when inference sequence lengths…

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to…

Recent deep models for image shadow removal often rely on attention-based architectures to capture long-range dependencies. However, their fixed attention patterns tend to mix illumination cues from irrelevant regions, leading to distorted…

In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design.…

Micro-gesture recognition (MGR) targets the identification of subtle and fine-grained human motions and requires accurate modeling of both long-range and local spatiotemporal dependencies. While CNNs are effective at capturing local…

Numerous CNN-Transformer hybrid models rely on high-complexity global attention mechanisms to capture long-range dependencies, which introduces non-linear computational complexity and leads to significant resource consumption. Although…

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…

The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. However, the inherent complexity of self-attention is quadratic to the size of the image,…

Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range…

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…