4 citations · 16 across the 20 of their papers we have counts for
20 papers
Seeing Through Smoke: Surgical Desmoking for Improved Visual Perception
Jingpei Lu, Fengyi Jiang, Xiaorui Zhang +2
Minimally invasive and robot-assisted surgery relies heavily on endoscopic imaging, yet surgical smoke produced by electrocautery and vessel-sealing instruments can severely degrad…
UNet-AF: Alias-free UNet architectures
Jérémy Scanvic, Quentin Barthélemy, Julián Tachella
The simplicity and effectiveness of UNet architectures make them ubiquitous in image restoration, segmentation, and diffusion models. They are often assumed to be equivariant to tr…
Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging
Victor Sechaud, Laurent Jacques, Patrice Abry +1
Learning based methods are now ubiquitous for solving inverse problems, but their deployment in real-world applications is often hindered by the lack of ground truth references for…
Self-Supervised Learning from Noisy and Incomplete Data
Julián Tachella, Mike Davies
Many important problems in science and engineering involve inferring a signal from noisy and/or incomplete observations, where the observation process is known. Historically, this…
Efficient Unrolled Networks for Large-Scale 3D Inverse Problems
Romain Vo, Julián Tachella
Deep learning-based methods have revolutionized the field of imaging inverse problems, yielding state-of-the-art performance across various imaging domains. The best performing net…
Equivariant Deep Equilibrium Models for Imaging Inverse Problems
Alexander Mehta, Ruangrawee Kitichotkul, Vivek K Goyal +1
Equivariant imaging (EI) enables training signal reconstruction models without requiring ground truth data by leveraging signal symmetries. Deep equilibrium models (DEQs) are a pow…
Structured Random Models for Phase Retrieval with Optical Diffusers
Zhiyuan Hu, Fakhriyya Mammadova, Julián Tachella +2
Phase retrieval is a nonlinear inverse problem that arises in a wide range of imaging modalities, from electron microscopy to Fourier ptychography. In particular, the reconstructio…
Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
Brett Levac, Jon Tamir, Marcelo Pereyra +1
Diffusion models (DMs) have rapidly emerged as a powerful framework for image generation and restoration. However, existing DMs are primarily trained in a supervised manner by usin…
Equivariant Splitting: Self-supervised learning from incomplete data
Victor Sechaud, Jérémy Scanvic, Quentin Barthélemy +2
Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learnin…
Self-supervised learning for phase retrieval
Victor Sechaud, Patrice Abry, Laurent Jacques +1
In recent years, deep neural networks have emerged as a solution for inverse imaging problems. These networks are generally trained using pairs of images: one degraded and the othe…
Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networks
Jérémy Scanvic, Quentin Barthélemy, Julián Tachella
The design of convolutional neural architectures that are exactly equivariant to continuous translations is an active field of research. It promises to benefit scientific computing…
DeepInverse: A Python package for solving imaging inverse problems with deep learning
Julián Tachella, Matthieu Terris, Samuel Hurault +24
DeepInverse is an open-source PyTorch-based library for solving imaging inverse problems. The library covers all crucial steps in image reconstruction from the efficient implementa…
Reconstruct Anything Model: a lightweight general model for computational imaging
Matthieu Terris, Samuel Hurault, Maxime Song +1
Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods…
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
Brayan Monroy, Jorge Bacca, Julián Tachella
Recorrupted-to-Recorrupted (R2R) has emerged as a methodology for training deep networks for image restoration in a self-supervised manner from noisy measurement data alone, demons…
Structured Random Model for Fast and Robust Phase Retrieval
Zhiyuan Hu, Julián Tachella, Michael Unser +1
Phase retrieval, a nonlinear problem prevalent in imaging applications, has been extensively studied using random models, some of which with i.i.d. sensing matrix components. While…
Equivariance-based self-supervised learning for audio signal recovery from clipped measurements
Victor Sechaud, Laurent Jacques, Patrice Abry +1
In numerous inverse problems, state-of-the-art solving strategies involve training neural networks from ground truth and associated measurement datasets that, however, may be expen…
UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate
Julián Tachella, Mike Davies, Laurent Jacques
Recently, many self-supervised learning methods for image reconstruction have been proposed that can learn from noisy data alone, bypassing the need for ground-truth references. Mo…
Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and Deblurring
Jérémy Scanvic, Mike Davies, Patrice Abry +1
Self-supervised methods have recently proved to be nearly as effective as supervised ones in various imaging inverse problems, paving the way for learning-based approaches in scien…
Equivariant plug-and-play image reconstruction
Matthieu Terris, Thomas Moreau, Nelly Pustelnik +1
Plug-and-play algorithms constitute a popular framework for solving inverse imaging problems that rely on the implicit definition of an image prior via a denoiser. These algorithms…
Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems
Julian Tachella, Marcelo Pereyra
Scientific imaging problems are often severely ill-posed, and hence have significant intrinsic uncertainty. Accurately quantifying the uncertainty in the solutions to such problems…