Publications related to GECCO: Geometrically-Conditioned Point Diffusion Models

Related publications (23)

Multilingual Vision-Language Pre-training for the Remote Sensing Domain

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific domain has relied on ...

Association for Computing Machinery, Inc2024

Ice multiplication from ice-ice collisions in the high Arctic: sensitivity to ice habit, rimed fraction, ice type and uncertainties in the numerical description of the process

Athanasios Nenes, Georgia Sotiropoulou

Atmospheric models often fail to correctly reproduce the microphysical structure of Arctic mixed-phase clouds and underpredict ice water content even when the simulations are constrained by observed levels of ice nucleating particles. In this study we inve ...

Copernicus GmbH2021

Rethinking Personalized Client Collaboration in Federated Learning

Anne-Marie Kermarrec

Federated Learning (FL) has gained considerable attention recently, as it allows clients to cooperatively train a global machine learning model without sharing raw data. However, its performance can be compromised due to the high heterogeneity in clients' ...

2024

An overview of the ORACLES (ObseRvations of Aerosols above CLouds and their intEractionS) project: aerosol-cloud-radiation interactions in the southeast Atlantic basin

Athanasios Nenes

Southern Africa produces almost a third of the Earth's biomass burning (BB) aerosol particles, yet the fate of these particles and their influence on regional and global climate is poorly understood. ORACLES (ObseRvations of Aerosols above CLouds and their ...

Copernicus GmbH2021

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Julian Thomas Blackwell, Tanja Christina Käser Jacober, Paola Mejia Domenzain, Vinitra Swamy

Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging w ...

2024

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Alexander Mathis, Alberto Silvio Chiappa, Alessandro Marin Vargas, Axel Bisi

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Zenodo2024

Improved Representation of Clouds in the Atmospheric Component LMDZ6A of the IPSL-CM6A Earth System Model

Etienne Gabriel Henri Vignon

The cloud parameterizations of the LMDZ6A climate model (the atmospheric component of the IPSL-CM6 Earth system model) are entirely described, and the global cloud distribution and cloud radiative effects are evaluated against the CALIPSO-CloudSat and CERE ...

2020

Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields With a Generative Adversarial Network

Alexis Berne, Jussi Sakari Leinonen

Generative adversarial networks (GANs) have been recently adopted for super-resolution, an application closely related to what is referred to as "downscaling'' in the atmospheric sciences: improving the spatial resolution of low-resolution images. The abil ...

2020

LMDZ6A: The Atmospheric Component of the IPSL Climate Model With Improved and Better Tuned Physics

Etienne Gabriel Henri Vignon

This study presents the version of the LMDZ global atmospheric model used as the atmospheric component of the Institut Pierre Simon Laplace coupled model (IPSL-CM6A-LR) to contribute to the 6th phase of the international Coupled Model Intercomparison Proje ...

2020

Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network

Jussi Sakari Leinonen

We demonstrate the feasibility of solving atmospheric remote sensing problems with machine learning using conditional generative adversarial networks (CGANs), implemented using convolutional neural networks. We apply the CGAN to generating two-dimensional ...

AMER GEOPHYSICAL UNION2019

Cloud condensation nuclei activity of six pollenkitts and the influence of their surface activity

Athanasios Nenes

The role of surfactants in governing water interactions of atmospheric aerosols has been a recurring topic in cloud microphysics for more than two decades. Studies of detailed surface thermodynamics are limited by the availability of aerosol samples for ex ...

Copernicus Publications2019

Variational Methods for Human Modeling

Timur Bagautdinov

A large part of computer vision research is devoted to building models and algorithms aimed at understanding human appearance and behaviour from images and videos. Ultimately, we want to build automated systems that are at least as capable as people when i ...

EPFL2018

Measurements of precipitation in Dumont d'Urville, Adelie Land, East Antarctica

Alexis Berne, Jacopo Grazioli

The first results of a campaign of intensive observation of precipitation in Dumont d'Urville, Antarctica, are presented. Several instruments collected data from November 2015 to February 2016 or longer, including a polarimetric radar (MXPol), a Micro Rain ...

Copernicus GmbH2017

Geometrically-Conditioned Point Diffusion Models

Pascal Fua, Eduard Trulls Fortuny, Michal Jan Tyszkiewicz

Diffusion models generating images conditionally on text, such as Dall-E 2 [51] and Stable Diffusion[53], have recently made a splash far beyond the computer vision com- munity. Here, we tackle the related problem of generating point clouds, both unconditi ...

2023

Applications of Approximate Learning and Inference for Probabilistic Models

Young Jun Ko

We develop approximate inference and learning methods for facilitating the use of probabilistic modeling techniques motivated by applications in two different areas. First, we consider the ill-posed inverse problem of recovering an image from an underdeter ...

EPFL2017

The role of secondary ice production in mixed-phase clouds

Paraskevi Georgakaki

Clouds are omnipresent in the Earth's atmosphere. Their phase composition significantly modulates their interaction with solar and terrestrial radiation, as well as precipitation formation. Particularly for clouds containing both phases, known as mixed-pha ...

EPFL2023

Dense Multitask Learning to Reconfigure Comics

Sabine Süsstrunk, Mathieu Salzmann, Deblina Bhattacharjee

In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comic panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narrativ ...

IEEE2023

Phase Retrieval: From Computational Imaging to Machine Learning: A tutorial

Michaël Unser, Thanh-An Michel Pham, Jonathan Yuelin Dong

Phase retrieval consists in the recovery of a complex-valued signal from intensity-only measurements. As it pervades a broad variety of applications, many researchers have striven to develop phase-retrieval algorithms. Classical approaches involve techniqu ...

2023

Center-Based Decoupled Point Cloud Registration for 6D Object Pose Estimation

Mathieu Salzmann, Jiancheng Yang, Zheng Dang

In this paper, we propose a novel center-based decoupled point cloud registration framework for robust 6D object pose estimation in real-world scenarios. Our method decouples the translation from the entire transformation by predicting the object center an ...

Ieee Computer Soc2023

Efficient compressed sensing reconstruction for 3D fluorescence microscopy using OptoMechanical Modulation Tomography (OMMT) with a 1+2D regularization

François Thierry M Marelli

OptoMechanical Modulation Tomography (OMMT) exploits compressed sensing to reconstruct high resolution microscopy volumes from fewer measurement images compared to exhaustive section sampling in conventional light sheet microscopy. Nevertheless, the volume ...

2023