Related papers: LP-IOANet: Efficient High Resolution Document Shad…

Document denoising is considered one of the most challenging tasks in computer vision. There exist millions of documents that are still to be digitized, but problems like document degradation due to natural and man-made factors make this…

This paper aims to remove specular highlights from a single object-level image. Although previous methods have made some progresses, their performance remains somewhat limited, particularly for real images with complex specular highlights.…

There is a growing consensus in the research community that the optimization of low-light image enhancement approaches should be guided by the visual quality perceived by end users. Despite the substantial efforts invested in the design of…

We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow,…

Efficient deep learning-based approaches have achieved remarkable performance in single image super-resolution. However, recent studies on efficient super-resolution have mainly focused on reducing the number of parameters and…

Semantic segmentation for extracting buildings and roads from uncrewed aerial vehicle (UAV) remote sensing images by deep learning becomes a more efficient and convenient method than traditional manual segmentation in surveying and mapping…

Adverse conditions like snow, rain, nighttime, and fog, pose challenges for autonomous driving perception systems. Existing methods have limited effectiveness in improving essential computer vision tasks, such as semantic segmentation, and…

4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high…

Remote sensing shadow removal, which aims to recover contaminated surface information, is tricky since shadows typically display overwhelmingly low illumination intensities. In contrast, the infrared image is robust toward significant light…

We propose a novel method of efficient upsampling of a single natural image. Current methods for image upsampling tend to produce high-resolution images with either blurry salient edges, or loss of fine textural detail, or spurious noise…

Augmented Reality (AR) applications necessitates methods of inserting needed objects into scenes captured by cameras in a way that is coherent with the surroundings. Common AR applications require the insertion of predefined 3D objects with…

Low-light conditions pose significant challenges for both human and machine annotation. This in turn has led to a lack of research into machine understanding for low-light images and (in particular) videos. A common approach is to apply…

We propose a simple extension of residual networks that works simultaneously in multiple resolutions. Our network design is inspired by the iterative back-projection algorithm but seeks the more difficult task of learning how to enhance…

Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved. However, we found out that most of these methods could not…

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing…

Small object detection is challenging because small objects do not contain detailed information and may even disappear in the deep network. Usually, feeding high-resolution images into a network can alleviate this issue. However, simply…

3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level…

Low-light imaging on mobile devices is typically challenging due to insufficient incident light coming through the relatively small aperture, resulting in a low signal-to-noise ratio. Most of the previous works on low-light image processing…

Deep learning (DL) has revolutionized the field of document image analysis, showcasing superhuman performance across a diverse set of tasks. However, the inherent black-box nature of deep learning models still presents a significant…

Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…