Skip to yearly menu bar Skip to main content

( events)   Timezone:  
Fri Dec 11 07:30 AM -- 04:00 PM (PST)
Workshop on Deep Learning and Inverse Problems
Reinhard Heckel · Paul Hand · Richard Baraniuk · Lenka Zdeborov√° · Soheil Feizi

Workshop Home Page

Learning-based methods, and in particular deep neural networks, have emerged as highly successful and universal tools for image and signal recovery and restoration. They achieve state-of-the-art results on tasks ranging from image denoising, image compression, and image reconstruction from few and noisy measurements. They are starting to be used in important imaging technologies, for example in GEs newest computational tomography scanners and in the newest generation of the iPhone.

The field has a range of theoretical and practical questions that remain unanswered. In particular, learning and neural network-based approaches often lack the guarantees of traditional physics-based methods. Further, while superior on average, learning-based methods can make drastic reconstruction errors, such as hallucinating a tumor in an MRI reconstruction or turning a pixelated picture of Obama into a white male.

This virtual workshop aims at bringing together theoreticians and practitioners in order to chart out recent advances and discuss new directions in deep neural network-based approaches for solving inverse problems in the imaging sciences and beyond. NeurIPS, with its visibility and attendance by experts in machine learning, offers the ideal frame for this exchange of ideas. We will use this virtual format to make this topic accessible to a broader audience than the in-person meeting is able to as described below.

Newcomer presentation (Talk and Q&A)
Opening Remarks
Victor Lempitsky - Generative Models for Landscapes and Avatars (Invited talk and Q&A)
Thomas Pock - Variational Networks (Invited talk and Q&A)
Risk Quantification in Deep MRI Reconstruction (Contributed Talk and Q&A)
GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images (Contributed Talk and Q&A)
Discussion (Break and Discussion)
Rebecca Willett - Model Adaptation for Inverse Problems in Imaging (Invited talk and Q&A)
Stefano Emron - Generative Modeling via Denoising (Invited talk and Q&A)
Compressed Sensing with Approximate Priors via Conditional Resampling (Contributed Talk and Q&A)
Chris Metzler - Approximate Message Passing (AMP) Algorithms for Computational Imaging (Invited Talk and Q&A)
Poster Session
Peyman Milanfar - Denoising as Building Block Theory and Applications (Invited talk and Q&A)
Rachel Ward (Invited talk and Q&A)
Larry Zitnick - fastMRI (Invited talk and Q&A)