publications and talks

2025

1. arxiv

   

   How Diffusion Prior Landscapes Shape the Posterior in Blind Deconvolution

   Minh-Hai Nguyen, Edouard Pauwels, and Pierre Weiss

   2025

   Abstract Bib PDF

   The Maximum A Posteriori (MAP) estimation is a widely used framework in blind deconvolution to recover sharp images from blurred observations. The estimated image and blur filter are defined as the maximizer of the posterior distribution. However, when paired with sparsity-promoting image priors, MAP estimation has been shown to favors blurry solutions, limiting its effectiveness. In this paper, we revisit this result using diffusion-based priors, a class of models that capture realistic image distributions. Through an empirical examination of the prior’s likelihood landscape, we uncover two key properties: first, blurry images tend to have higher likelihoods; second, the landscape contains numerous local minimizers that correspond to natural images. Building on these insights, we provide a theoretical analysis of the blind deblurring posterior. This reveals that the MAP estimator tends to produce sharp filters (close to the Dirac delta function) and blurry solutions. However local minimizers of the posterior, which can be obtained with gradient descent, correspond to realistic, natural images, effectively solving the blind deconvolution problem. Our findings suggest that overcoming MAP’s limitations requires good local initialization to local minima in the posterior landscape. We validate our analysis with numerical experiments, demonstrating the practical implications of our insights for designing improved priors and optimization techniques.

   @misc{nguyen2025diffusionpriorlandscapesshape,
     title = {How Diffusion Prior Landscapes Shape the Posterior in Blind Deconvolution},
     author = {Nguyen, Minh-Hai and Pauwels, Edouard and Weiss, Pierre},
     year = {2025},
     eprint = {2508.02923},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     url = {https://arxiv.org/abs/2508.02923},
   }

2. DeepInverse: A Python package for solving imaging inverse problems with deep learning

   Julián Tachella, Matthieu Terris, Samuel Hurault, and 24 more authors

   2025

2024

1. IEEE TGRS

   DeepVibes: Correcting Microvibrations in Satellite Imaging With Pushbroom Cameras

   Minh Hai Nguyen, François Vieilleville, and Pierre Weiss

   IEEE Transactions on Geoscience and Remote Sensing, 2024

   Abstract Bib HTML PDF

   In this paper, we propose new algorithms for estimating micro-vibrations and correcting its effects in satellite imaging with linear pushbroom camera. We first design an accurate model of the acquisition process with linear pushbroom camera, that incorporates the satellite attitude as parameters. We then propose a two stage reconstruction method based on an identification neural network to identify the attitude, followed by a deep unrolled network to correct the micro-vibrations. We then evalu- ate the proposed framework on synthetic and real data, showing promising results for this challenging problem. Our results highlight the critical role of the focal plane’s geometry, to improve the micro-vibrations identifiability and therefore, the reconstruction quality.

   @article{10559627,
     author = {Nguyen, Minh Hai and de Vieilleville, François and Weiss, Pierre},
     journal = {IEEE Transactions on Geoscience and Remote Sensing},
     title = {DeepVibes: Correcting Microvibrations in Satellite Imaging With Pushbroom Cameras},
     year = {2024},
     volume = {62},
     number = {},
     pages = {1-9},
     keywords = {Cameras;Satellites;Noise;Vibrations;Orbits;Mathematical models;Charge coupled devices;Convolutional neural network (CNN);jitter;microvibration;pushbroom;satellite imaging;unrolled network},
     doi = {10.1109/TGRS.2024.3415372},
     pdf = pub_vibrations.pdf,
   }

2. preprint

   Comparing Plug-and-Play and Unrolled networks

   Minh Hai Nguyen, and Pierre Weiss

   preprint, 2024

   Abstract Bib PDF

   Plug-and-play and unrolled methods are among the most popular and efficient approaches for solving inverse problems in imaging. In this paper, we review their similarities and differences. We adopt a Bayesian framework to explain their statistical properties. This allows us to relate plug-and-play methods to Maximum A Posteriori (MAP) estimators and unrolled networks to Minimum Mean Square Error (MMSE) estimators. We clarify some of their properties including their stability and numerical efficiency. Overall, this paper provides a concise review of their respective advantages and limitations.

   @article{nguyen2024pnp-unrolled,
     title = {Comparing Plug-and-Play and Unrolled networks},
     author = {Nguyen, Minh Hai and Weiss, Pierre},
     year = {2024},
     journal = {preprint},
     pdf = pub_pnp_unrolled.pdf,
   }

2025

1. Poster

   Blind deconvolution in Optical Microscopy

   IABM: Colloque Français d’Intelligence Artificielle en Imagerie Biomédicale, Nice, France, 2025

   PDF

2025

1. Talk

   Blind deconvolution in Optical Microscopy

   PhD Seminar, IRIT, 20 Mars 2025, Toulouse, France. , 2025

   PDF

2023

1. Talk

   DeepVibes: Correcting Microvibrations in Satellite Imaging With Pushbroom Cameras

   Conference: 30 years of Mathematical for Optical Imaging, 27 Sep 2024, Marseille, France., 2023