相关论文: Ghost-free High Dynamic Range Imaging with Context…

Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed…

While convolutional neural networks (CNNs) and vision transformers (ViTs) have advanced medical image segmentation, they face inherent limitations such as local receptive fields in CNNs and high computational complexity in ViTs. This paper…

Leveraging Transformer attention has led to great advancements in HDR deghosting. However, the intricate nature of self-attention introduces practical challenges, as existing state-of-the-art methods often demand high-end GPUs or exhibit…

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. Traditionally, convolutional neural networks (CNNs) dominated this domain,…

High-resolution imagery is essential for accurate 3D reconstruction, as many geometric details only emerge at fine spatial scales. Recent feed-forward approaches, such as the Visual Geometry Grounded Transformer (VGGT), have demonstrated…

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of…

Scene understanding plays an important role in several high-level computer vision applications, such as autonomous vehicles, intelligent video surveillance, or robotics. However, too few solutions have been proposed for indoor/outdoor scene…

In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach…

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many different 2D medical image analysis tasks. In clinical practice, however, a large part of the medical imaging data available is in 3D. This has…

Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to…

High dynamic range (HDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects…

High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offers various data-driven methods for HDR image reconstruction…

Snapshot compressive imaging (SCI) encodes high-speed scene video into a snapshot measurement and then computationally makes reconstructions, allowing for efficient high-dimensional data acquisition. Numerous algorithms, ranging from…

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Rendering realistic images with global illumination is a computationally demanding task and often requires dedicated hardware for feasible runtime. Recent research uses Deep Neural Networks to predict indirect lighting on image level, but…

Conventional image sensors have limited dynamic range, causing saturation in high-dynamic-range (HDR) scenes. Modulo cameras address this by folding incident irradiance into a bounded range, yet require specialized unwrapping algorithms to…

High Dynamic Range (HDR) generation remains challenging for generative models, which are largely limited to low dynamic range outputs. Recent diffusionbased approaches approximate HDR by generating multiple exposure-conditioned samples,…

Camera sensors can only capture a limited range of luminance simultaneously, and in order to create high dynamic range (HDR) images a set of different exposures are typically combined. In this paper we address the problem of predicting…

Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating…

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…