Related papers: Zoom To Learn, Learn To Zoom
Deep learning-based super-resolution models have the potential to revolutionize biomedical imaging and diagnoses by effectively tackling various challenges associated with early detection, personalized medicine, and clinical automation.…
Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and…
Robot navigation in mapless environment is one of the essential problems and challenges in mobile robots. Deep reinforcement learning is a promising technique to tackle the task of mapless navigation. Since reinforcement learning requires a…
Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic…
Learning super-resolution (SR) network without the paired low resolution (LR) and high resolution (HR) image is difficult because direct supervision through the corresponding HR counterpart is unavailable. Recently, many real-world SR…
Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most existing methods train a dehazing model on synthetic hazy images, which are less able to generalize well to real hazy…
Estimation of optical aberrations from volumetric intensity images is a key step in sensorless adaptive optics for 3D microscopy. Recent approaches based on deep learning promise accurate results at fast processing speeds. However,…
We propose a method for sim-to-real robot learning which exploits simulator state information in a way that scales to many objects. We first train a pair of encoder networks to capture multi-object state information in a latent space. One…
Many perception systems in mobile computing, autonomous navigation, and AR/VR face strict compute constraints that are particularly challenging for high-resolution input images. Previous works propose nonuniform downsamplers that "learn to…
Deep neural networks have been very successful in image estimation applications such as compressive-sensing and image restoration, as a means to estimate images from partial, blurry, or otherwise degraded measurements. These networks are…
The use of synthetic data for training computer vision algorithms has become increasingly popular due to its cost-effectiveness, scalability, and ability to provide accurate multi-modality labels. Although recent studies have demonstrated…
We use reinforcement learning in simulation to obtain a driving system controlling a full-size real-world vehicle. The driving policy takes RGB images from a single camera and their semantic segmentation as input. We use mostly synthetic…
Recently, deep learning-based single image reflection separation methods have been exploited widely. To benefit the learning approach, a large number of training image pairs (i.e., with and without reflections) were synthesized in various…
Radars and cameras are mature, cost-effective, and robust sensors and have been widely used in the perception stack of mass-produced autonomous driving systems. Due to their complementary properties, outputs from radar detection (radar…
Deep Learning-based 2D/3D registration enables fast, robust, and accurate X-ray to CT image fusion when large annotated paired datasets are available for training. However, the need for paired CT volume and X-ray images with ground truth…
Simulating realistic radar data has the potential to significantly accelerate the development of data-driven approaches to radar processing. However, it is fraught with difficulty due to the notoriously complex image formation process. Here…
In this project, we propose a novel approach for estimating depth from RGB images. Traditionally, most work uses a single RGB image to estimate depth, which is inherently difficult and generally results in poor performance, even with…
Deep neural networks have exhibited promising performance in image super-resolution (SR) due to the power in learning the non-linear mapping from low-resolution (LR) images to high-resolution (HR) images. However, most deep learning methods…
Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. To obtain poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular…
Saliency detection methods are central to several real-world applications such as robot navigation and satellite imagery. However, the performance of existing methods deteriorate under low-light conditions because training datasets mostly…