Search Results for author:
Found 12 papers, 7 papers with code
Diffusion models meet image counter-forensics
We show that diffusion purification methods are well suited for counter-forensics tasks.
Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks
Then, a second network trained jointly with the first one, unrolls a non-blind deconvolution method using the motion kernel field estimated by the first network.
U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold
In this work we propose a non-contrastive method for anomaly detection and segmentation in images, that benefits both from a modern machine learning approach and a more classic statistical detection theory.
Rethinking Motion Deblurring Training: A Segmentation-Based Method for Simulating Non-Uniform Motion Blurred Images
Successful training of end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images.
A Contrario multi-scale anomaly detection method for industrial quality inspection
In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions.
A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection
In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions.
Non-uniform Blur Kernel Estimation via Adaptive Basis Decomposition
In recent years, the removal of motion blur in photographs has seen impressive progress in the hands of deep learning-based methods, trained to map directly from blurry to sharp images.
Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
In this paper we address the problem of solving ill-posed inverse problems in imaging where the prior is a neural generative model.
OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification.
A Bayesian Hyperprior Approach for Joint Image Denoising and Interpolation, with an Application to HDR Imaging
In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure.
Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching
We also present results on multimodal graphs and applications to collaborative inference of brain connectivity from alignment-free functional magnetic resonance imaging (fMRI) data.
Topology Constraints in Graphical Models
Graphical models are a very useful tool to describe and understand natural phenomena, from gene expression to climate change and social interactions.
