Related papers: DPT: Deformable Patch-based Transformer for Visual…

Image identification is one of the most challenging tasks in different areas of computer vision. Scale-invariant feature transform is an algorithm to detect and describe local features in images to further use them as an image matching…

Removing noise from images is a challenging and fundamental problem in the field of computer vision. Images captured by modern cameras are inevitably degraded by noise which limits the accuracy of any quantitative measurements on those…

Like other applications in computer vision, medical image segmentation has been most successfully addressed using deep learning models that rely on the convolution operation as their main building block. Convolutions enjoy important…

Vision Transformers rely on fixed patch tokens that ignore the spatial and semantic structure of images. In this work, we introduce an end-to-end differentiable tokenizer that adapts to image content with pixel-level granularity while…

We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO). DPVO uses a novel recurrent network architecture designed for tracking image patches across time. Recent approaches to VO have…

Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models…

Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent progress has demonstrated that combining such Transformers…

Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

Deepfake is the manipulated video made with a generative deep learning technique such as Generative Adversarial Networks (GANs) or Auto Encoder that anyone can utilize. Recently, with the increase of Deepfake videos, some classifiers…

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale…

Segmentation maps of medical images annotated by medical experts contain rich spatial information. In this paper, we propose to decompose annotation maps to learn disentangled and richer feature transforms for segmentation problems in…

In this work, we present Multiformer, a novel approach to depth-aware video panoptic segmentation (DVPS) based on the mask transformer paradigm. Our method learns object representations that are shared across segmentation, monocular depth…

Recent years have witnessed the great success of vision transformer (ViT), which has achieved state-of-the-art performance on multiple computer vision benchmarks. However, ViT models suffer from vast amounts of parameters and high…

Deformable objects often appear in unstructured configurations. Tracing deformable objects helps bringing them into extended states and facilitating the downstream manipulation tasks. Due to the requirements for object-specific modeling or…

Automatic medical image segmentation has made great progress benefit from the development of deep learning. However, most existing methods are based on convolutional neural networks (CNNs), which fail to build long-range dependencies and…

Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this whilst retaining the fast inference speed of deep learning, we…

This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is…

Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained…

The acquisition conditions for low-dose and high-dose CT images are usually different, so that the shifts in the CT numbers often occur. Accordingly, unsupervised deep learning-based approaches, which learn the target image distribution,…