9 papers
Reconstruction-Aware Distribution Matching for Inverse Problems with Unpaired Data
Thomas Ryckeboer, Giacomo Meanti, Julien Mairal
Recovering the forward operator of an imaging system from unpaired data avoids both calibration hardware and the clean/degraded pairs that supervision requires-pairs that, for a re…
Directly Optimizing Mean Demographic Parity for Nonlinear Regression
Ieva Petrulionyte, Julien Mairal, Michael Arbel
We focus on regression settings where the fairness goal is to equalize average predictions across values of a sensitive attribute, a criterion known as mean demographic parity. Dir…
SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining
Nassim Ait Ali Braham, Aaron Banze, Conrad M. Albrecht +3
Earth observation (EO) foundation models (FMs) are increasingly trained on multisensor data, spanning multispectral imagery (MSI), synthetic aperture radar (SAR), and derived geosp…
Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
Kenta Vert, Giacomo Meanti, Scott Pesme +2
Plug-and-Play (PnP) methods have become standard tools for solving imaging inverse problems by replacing the intractable maximum a posteriori (MAP) denoiser with the MMSE one. Whil…
Non-Stationary Functional Bilevel Optimization
Jason Bohne, Ieva Petrulionyte, Michael Arbel +2
Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static offline settings and per…
MAP Estimation with Denoisers: Convergence Rates and Guarantees
Scott Pesme, Giacomo Meanti, Michael Arbel +1
Denoiser models have become powerful tools for inverse problems, enabling the use of pretrained networks to approximate the score of a smoothed prior distribution. These models are…
Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
Giacomo Meanti, Thomas Ryckeboer, Michael Arbel +1
This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowl…
LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes
Juliette Marrie, Romain Menegaux, Michael Arbel +2
We address the problem of extending the capabilities of vision foundation models such as DINO, SAM, and CLIP, to 3D tasks. Specifically, we introduce a novel method to uplift 2D im…
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models
Juliette Marrie, Michael Arbel, Julien Mairal +1
Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks. Yet, real-world applications often demand compact models tailored to specific pro…