Related papers: Shadow-Aware Dynamic Convolution for Shadow Remova…

Monocular depth estimation is known as an ill-posed task in which objects in a 2D image usually do not contain sufficient information to predict their depth. Thus, it acts differently from other tasks (e.g., classification and segmentation)…

Short-and-sparse deconvolution (SaSD) is the problem of extracting localized, recurring motifs in signals with spatial or temporal structure. Variants of this problem arise in applications such as image deblurring, microscopy, neural spike…

Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal datasets, current methods are prone to overfitting training data,…

RGB-D semantic segmentation has attracted increasing attention over the past few years. Existing methods mostly employ homogeneous convolution operators to consume the RGB and depth features, ignoring their intrinsic differences. In fact,…

Deep neural networks face several challenges in hyperspectral image classification, including insufficient utilization of joint spatial-spectral information, gradient vanishing with increasing depth, and overfitting. To enhance feature…

Image attribution algorithms aim to identify important regions that are highly relevant to model decisions. Although existing attribution solutions can effectively assign importance to target elements, they still face the following…

Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently. However, most existing models can not effectively explore spatial information and spectral information between bands simultaneously,…

Low-light images suffer from complex degradation, and existing enhancement methods often encode all degradation factors within a single latent space. This leads to highly entangled features and strong black-box characteristics, making the…

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…

Convolution is spatially-symmetric, i.e., the visual features are independent of its position in the image, which limits its ability to utilize contextual cues for visual recognition. This paper addresses this issue by introducing a…

Majority of deep learning methods utilize vanilla convolution for enhancing underwater images. While vanilla convolution excels in capturing local features and learning the spatial hierarchical structure of images, it tends to smooth input…

Existing unsupervised methods have addressed the challenges of inconsistent paired data and tedious acquisition of ground-truth labels in shadow removal tasks. However, GAN-based training often faces issues such as mode collapse and…

The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixel-wise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the twilight as the…

Spatially variant dynamic convolution provides a principled approach of integrating spatial adaptivity into deep neural networks. However, mainstream designs in medical segmentation commonly generate dynamic kernels through average pooling,…

3D reconstruction is a fundamental problem in computer vision, and the task is especially challenging when the object to reconstruct is partially or fully occluded. We introduce a method that uses the shadows cast by an unobserved object in…

Shadows are a prevalent problem in remote sensing imagery (RSI), degrading visual quality and severely limiting the performance of downstream tasks like object detection and semantic segmentation. Most prior works treat shadow detection and…

Sonar imaging is fundamental to underwater exploration, with critical applications in defense, navigation, and marine research. Shadow regions, in particular, provide essential cues for object detection and classification, yet existing…

Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs…

We address the problem of decomposing a single image into reflectance and shading. The difficulty comes from the fact that the components of image---the surface albedo, the direct illumination, and the ambient illumination---are coupled…

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource…