Related papers: MatteViT: High-Frequency-Aware Document Shadow Rem…
Face manipulation detection has been receiving a lot of attention for the reliability and security of the face images/videos. Recent studies focus on using auxiliary information or prior knowledge to capture robust manipulation traces,…
Imaging through dense fog presents unique challenges, with essential visual information crucial for applications like object detection and recognition obscured, thereby hindering conventional image processing methods. Despite improvements…
Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a…
Face manipulation detection has been receiving a lot of attention for the reliability and security of the face images. Recent studies focus on using auxiliary information or prior knowledge to capture robust manipulation traces, which are…
Low-light video enhancement is highly demanding in maintaining spatiotemporal color consistency. Therefore, improving the accuracy of color mapping and keeping the latency low is challenging. Based on this, we propose incorporating…
Capturing images is a key part of automation for high-level tasks such as scene text recognition. Low-light conditions pose a challenge for high-level perception stacks, which are often optimized on well-lit, artifact-free images.…
Vision transformers have become one of the most important models for computer vision tasks. Although they outperform prior works, they require heavy computational resources on a scale that is quadratic to the number of tokens, $N$. This is…
Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…
Image matting is an important computer vision problem. Many existing matting methods require a hand-made trimap to provide auxiliary information, which is very expensive and limits the real world usage. Recently, some trimap-free methods…
Despite its clinical utility, medical image segmentation (MIS) remains a daunting task due to images' inherent complexity and variability. Vision transformers (ViTs) have recently emerged as a promising solution to improve MIS; however,…
Modern microscopy routinely produces gigapixel images that contain structures across multiple spatial scales, from fine cellular morphology to broader tissue organization. Many analysis tasks require combining these scales, yet most vision…
Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…
Depth maps captured by modern depth cameras such as Kinect and Time-of-Flight (ToF) are usually contaminated by missing data, noises and suffer from being of low resolution. In this paper, we present a robust method for high-quality…
A novel method of contrast enhancement is proposed for underexposed images, in which heavy noise is hidden. Under low light conditions, images taken by digital cameras have low contrast in dark or bright regions. This is due to a limited…
Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation. Given feature map projections from multiple views onto a common ground plane, the state-of-the-art method…
This paper presents a novel approach for segmenting moving objects in unconstrained environments using guided convolutional neural networks. This guiding process relies on foreground masks from independent algorithms (i.e. state-of-the-art…
High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While…
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…
While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…
Video restoration for noise removal, deblurring or super-resolution is attracting more and more attention in the fields of image processing and computer vision. Works on video restoration with data-driven approaches for fog removal are rare…