Related papers: Self-Supervised Generative Adversarial Network for…
We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires monocular endoscopic videos…
Depth Estimation plays a crucial role in recent applications in robotics, autonomous vehicles, and augmented reality. These scenarios commonly operate under constraints imposed by computational power. Stereo image pairs offer an effective…
We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular,…
In this paper, we introduce a generative model for image enhancement specifically for improving diver detection in the underwater domain. In particular, we present a model that integrates generative adversarial network (GAN)-based image…
Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is…
Generative adversarial networks have gained a lot of attention in the computer vision community due to their capability of data generation without explicitly modelling the probability density function. The adversarial loss brought by the…
This work addresses the problems of semantic segmentation and image super-resolution by jointly considering the performance of both in training a Generative Adversarial Network (GAN). We propose a novel architecture and domain-specific…
Compared to traditional methods, Deep Learning (DL) becomes a key technology for computer vision tasks. Synthetic data generation is an interesting use case for DL, especially in the field of medical imaging such as Magnetic Resonance…
The data scarcity problem in Electroencephalography (EEG) based affective computing results into difficulty in building an effective model with high accuracy and stability using machine learning algorithms especially deep learning models.…
In this paper, a novel strategy of Secure Steganograpy based on Generative Adversarial Networks is proposed to generate suitable and secure covers for steganography. The proposed architecture has one generative network, and two…
Anatomical landmark segmentation and pathology localization are important steps in automated analysis of medical images. They are particularly challenging when the anatomy or pathology is small, as in retinal images and cardiac MRI, or when…
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results…
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich…
Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this…
Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable results in a wide range of geometric tasks. However, most of them require per-pixel ground-truth keypoint correspondence data which is…
Generative Adversarial Networks have been employed successfully to generate high-resolution augmented images of size 1024^2. Although the augmented images generated are unprecedented, the training time of the model is exceptionally high.…
While Convolutional Neural Networks (CNNs) trained for image and video super-resolution (SR) regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks. One of their limitations is their lack of…
To realize the full potential of deep learning for medical imaging, large annotated datasets are required for training. Such datasets are difficult to acquire because labeled medical images are not usually available due to privacy issues,…
Visual odometry (VO) and SLAM have been using multi-view geometry via local structure from motion for decades. These methods have a slight disadvantage in challenging scenarios such as low-texture images, dynamic scenarios, etc. Meanwhile,…
In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion. Based on good performance of a recently developed model for super-resolution, i.e., deep…