Related papers: Segmentation Guided Sparse Transformer for Under-D…
Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Gating), which enables explicit perception of degradation…
Diffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. Diffusion-based inverse problem solvers generate reconstructions of exceptional visual quality from heavily…
By leveraging the blur-noise trade-off, imaging with non-uniform exposures largely extends the image acquisition flexibility in harsh environments. However, the limitation of conventional cameras in perceiving intra-frame dynamic…
Underwater Image Enhancement (UIE) technology aims to tackle the challenge of restoring the degraded underwater images due to light absorption and scattering. To address problems, a novel U-Net based Reinforced Swin-Convs Transformer for…
While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…
In recent years, the development of deep learning has been pushing image denoising to a new level. Among them, self-supervised denoising is increasingly popular because it does not require any prior knowledge. Most of the existing…
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional…
Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on…
Recent years have seen an increase in the use of gigapixel-level image and video capture systems and benchmarks with high-resolution wide (HRW) shots. However, unlike close-up shots in the MS COCO dataset, the higher resolution and wider…
Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local information. Many few-shot learning methods have…
Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…
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…
The scalability of high-fidelity video diffusion models (VDMs) is constrained by two key sources of redundancy: the quadratic complexity of global spatio-temporal attention and the computational overhead of long iterative denoising…
In this work, we present a new method for 3D face reconstruction from sparse-view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode…
Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-constrained devices. We…
Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…
Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…
The underwater propagation environment for visible light signals is affected by complex factors such as absorption, shadowing, and reflection, making it very challengeable to achieve effective underwater visible light communication (UVLC)…
Seismic data interpolation is a critical pre-processing step for improving seismic imaging quality and remains a focus of academic innovation. To address the computational inefficiencies caused by extensive iterative resampling in current…
In the context of inverse problems $\bf y = Ax$, sparse recovery offers a powerful paradigm shift by enabling the stable solution of ill-posed or underdetermined systems through the exploitation of structure, particularly sparsity. Sparse…