Related papers: FreqMamba: Viewing Mamba from a Frequency Perspect…
Different rain models and novel network structures have been proposed to remove rain streaks from single rainy images. In this work, we bring attention to the intrinsic priors and multi-scale features of the rainy images, and develop…
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…
Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called…
Vision Mamba offers linear complexity for long visual sequences, yet its performance depends critically on how a two-dimensional patch grid is serialized into a one-dimensional state-space recurrence. Raster-style scans disrupt spatial…
Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…
Mamba has emerged as a powerful model for efficiently addressing tasks involving temporal and spatial data. Regarding the escalating heterogeneity and dynamics in wireless networks, Mamba holds the potential to revolutionize wireless…
In underwater image enhancement (UIE), convolutional neural networks (CNN) have inherent limitations in modeling long-range dependencies and are less effective in recovering global features. While Transformers excel at modeling long-range…
Change detection in remote sensing images is an essential tool for analyzing a region at different times. It finds varied applications in monitoring environmental changes, man-made changes as well as corresponding decision-making and…
Hyperspectral Imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in Deep Learning (DL) and Transformer architectures for HSI…
The rapid evolution of deepfake generation technologies necessitates the development of robust face forgery detection algorithms. Recent studies have demonstrated that wavelet analysis can enhance the generalization abilities of forgery…
In this paper, we tackle the recently popular topic of generating 360-degree images given the conventional narrow field of view (NFoV) images that could be taken from a single camera or cellphone. This task aims to predict the reasonable…
Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as…
The purpose of image inpainting is to recover scratches and damaged areas using context information from remaining parts. In recent years, thanks to the resurgence of convolutional neural networks (CNNs), image inpainting task has made…
Motion style transfer is a significant research direction in the field of computer vision, enabling virtual digital humans to rapidly switch between different styles of the same motion, thereby significantly enhancing the richness and…
The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…
By optimizing the rate-distortion-realism trade-off, generative image compression approaches produce detailed, realistic images instead of the only sharp-looking reconstructions produced by rate-distortion-optimized models. In this paper,…
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…
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…
Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing for precise prediction of action trajectories. However, diffusion models typically rely on large…
Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global…