Related papers: MambaScope: Coarse-to-Fine Scoping for Efficient V…
Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an…
Image restoration aims to recover details and enhance contrast in degraded images. With the growing demand for high-quality imaging (\textit{e.g.}, 4K and 8K), achieving a balance between restoration quality and computational efficiency has…
Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision…
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…
The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and…
Image shadow removal is a typical low-level vision task. Shadows cause local brightness shifts, which reduce the performance of downstream vision tasks. Currently, Transformer-based shadow removal methods suffer from quadratic computational…
Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…
Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…
Burst image super-resolution (BISR) aims to enhance the resolution of a keyframe by leveraging information from multiple low-resolution images captured in quick succession. In the deep learning era, BISR methods have evolved from fully…
With the evolution of large language models, traditional Transformer models become computationally demanding for lengthy sequences due to the quadratic growth in computation with respect to the sequence length. Mamba, emerging as a…
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…
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…
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…
Vision mambas have demonstrated strong performance with linear complexity to the number of vision tokens. Their efficiency results from processing image tokens sequentially. However, most existing methods employ patch-based image…
U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…
Discrete video tokenization is essential for efficient autoregressive generative modeling due to the high dimensionality of video data. This work introduces a state-of-the-art discrete video tokenizer with two key contributions. First, we…
Despite the significant achievements of Vision Transformers (ViTs) in various vision tasks, they are constrained by the quadratic complexity. Recently, State Space Models (SSMs) have garnered widespread attention due to their global…
State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains challenging due to the non-sequential structure of visual data…
Current low-light image enhancement (LLIE) methods face significant limitations in simultaneously improving brightness while preserving semantic consistency, fine details, and computational efficiency. With the emergence of state-space…
Current image tampering localization methods primarily rely on Convolutional Neural Networks (CNNs) and Transformers. While CNNs suffer from limited local receptive fields, Transformers offer global context modeling at the expense of…