Browsing by Subject "Generative Adversarial Networks"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Enhancing Visual Perception in Noisy Environments using Generative Adversarial Networks
    (2018-08) Fabbri, Cameron
    Autonomous robots rely on a variety of sensors – acoustic, inertial, and visual – for intelligent decision making. Due to its non-intrusive, passive nature, and high information content, vision is an attractive sensing modality. However, many environments contain natural sources of visual noise such as snow, rain, dust, and other forms of distortion. This work focuses on the underwater environment, in which visual noise is a prominent component. Factors such as light refraction and absorption, suspended particles in the water, and color distortion affect the quality of visual data, resulting in noisy and distorted images. Autonomous Underwater Vehicles (AUVs) that rely on visual sensing thus face difficult challenges, and consequently exhibit poor performance on vision driven tasks. This thesis proposes a method to improve the quality of visual underwater scenes using Generative Adversarial Networks (GANs), with the goal of improving input to vision-driven behaviors further down the autonomy pipeline. Furthermore, we show how recently proposed methods are able to generate a dataset for the purpose of such underwater image restoration. For any visually-guided underwater robots, this improvement can result in increased safety and reliability through robust visual perception. To that effect, we present quantitative and qualitative data which demonstrates that images corrected through the proposed approach generate more visually appealing images, and also provide increased accuracy for a diver tracking algorithm.
  • Thumbnail Image
    Item
    Equivariance in GAN Critics
    (2019-05) Upadhyay, Yash
    Equivariance allows learning a representation that disentangles an entity or a feature from it's meta-properties. Spatially-equivariant representations lead to more detailed representations that can capture greater information from the image space in comparison to spatially-invariant representations. Convolutional Neural Networks, the current work-horses for image based analysis are built with baked-in spatial-invariance which helps in tasks like object detection. However, tasks like image synthesis that require learning an accurate manifold in order to generate visually accurate and diverse images would suffer due to the incorporated invariance. Equivariant architectures like Capsule Networks prove to be better critics for Generative Adversarial Networks as they learn disentangled representations of the meta-properties of the entities they represent. This helps the GANs to learn the data manifold much faster and therefore, synthesize visually accurate images in significantly lesser number of training samples and training epochs in comparison to GAN variants that use CNNs. Apart from proposing architectures that incorporate Capsule Networks into GANs, the thesis also assesses the effects of varying amounts of invariance over the quality and diversity of the images generated.