Deep image prior

Deep image prior is a type of convolutional neural network used to enhance a given image with no prior training data other than the image itself. A neural network is randomly initialized and used as prior to solve inverse problems such as noise reduction, super-resolution, and inpainting. Image statistics are captured by the structure of a convolutional image generator rather than by any previously learned capabilities. Inverse problems such as noise reduction, super-resolution, and inpainting can be formulated as the optimization task , where is an image, a corrupted representation of that image, is a task-dependent data term, and R(x) is the regularizer. This forms an energy minimization problem. Deep neural networks learn a generator/decoder which maps a random code vector to an image . The image corruption method used to generate is selected for the specific application. In this approach, the prior is replaced with the implicit prior captured by the neural network (where for images that can be produced by a deep neural networks and otherwise). This yields the equation for the minimizer and the result of the optimization process . The minimizer (typically a gradient descent) starts from a randomly initialized parameters and descends into a local best result to yield the restoration function. A parameter θ may be used to recover any image, including its noise. However, the network is reluctant to pick up noise because it contains high impedance while useful signal offers low impedance. This results in the θ parameter approaching a good-looking local optimum so long as the number of iterations in the optimization process remains low enough not to overfit data. Typically, the deep neural network model for deep image prior uses a U-Net like model without the skip connections that connect the encoder blocks with the decoder blocks. The authors in their paper mention that "Our findings here (and in other similar comparisons) seem to suggest that having deeper architecture is beneficial, and that having skip-connections that work so well for recognition tasks (such as semantic segmentation) is highly detrimental.

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (78)

Personnes associées (15)

Unités associées (13)

Concepts associés (1)

Cours associés (3)

Séances de cours associées (13)

CIVIL-459: Deep learning for autonomous vehicles

Deep Learning (DL) is the subset of Machine learning reshaping the future of transportation and mobility. In this class, we will show how DL can be used to teach autonomous vehicles to detect objects,

EE-623: Perception and learning from multimodal sensors

The course will cover different aspects of multimodal processing (complementarity vs redundancy; alignment and synchrony; fusion), with an emphasis on the analysis of people, behaviors and interaction

DH-406: Machine learning for DH

This course aims to introduce the basic principles of machine learning in the context of the digital humanities. We will cover both supervised and unsupervised learning techniques, and study and imple

L'apprentissage profond ou apprentissage en profondeur (en anglais : deep learning, deep structured learning, hierarchical learning) est un sous-domaine de l’intelligence artificielle qui utilise des réseaux neuronaux pour résoudre des tâches complexes grâce à des architectures articulées de différentes transformations non linéaires. Ces techniques ont permis des progrès importants et rapides dans les domaines de l'analyse du signal sonore ou visuel et notamment de la reconnaissance faciale, de la reconnaissance vocale, de la vision par ordinateur, du traitement automatisé du langage.

Explainable Face Verification via Feature-Guided Gradient Backpropagation

Touradj Ebrahimi, Yuhang Lu, Zewei Xu

Recent years have witnessed significant advance- ment in face recognition (FR) techniques, with their applications widely spread in people’s lives and security-sensitive areas. There is a growing need for reliable interpretations of decisions of such syste ...

2024

Towards Trustworthy Deep Learning for Image Reconstruction

Alexis Marie Frederic Goujon

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

EPFL2024

The Halos and Environments of Nearby Galaxies (HERON) survey IV. Complexity in the boxy galaxies NGC720 and NGC2768

The shapes of galaxies, their outer regions in particular, are important guideposts to their formation and evolution. In this work, we report on the discovery of strongly box-shaped morphologies of the otherwise well-studied elliptical and lenticular galax ...

Les Ulis Cedex A2024

Une nouvelle approche pour la détection rapide, profonde et étendue MOOC: Selected chapters form winterschool on multi-scale brain

Présente une nouvelle approche pour la détection rapide, profonde et à grande surface à l'aide de microscopie multiphotons multispots.

Modélisation generative: Alors, maintenant et demain?

Explore l'évolution de la modélisation générative, depuis les méthodes traditionnelles jusqu'aux progrès de pointe, en passant par les défis à relever et en envisageant les possibilités futures.

Réseaux neuronaux convolutifs : structure et régularisation CS-433: Machine learning

Explore les réseaux neuronaux convolutifs, l'augmentation des données, la dégradation du poids et le décrochage pour améliorer les performances du modèle.