Publications related to Graph-Based vs Depth-Based Data Representation for Multiview Images

A full characterization of invariant embeddability of unimodular planar graphs

When can a unimodular random planar graph be drawn in the Euclidean or the hyperbolic plane in a way that the distribution of the random drawing is isometry-invariant? This question was answered for one-ended unimodular graphs in Benjamini and Timar, using ...

WILEY2023

Equivariant Neural Architectures for Representing and Generating Graphs

Clément Arthur Yvon Vignac

Graph machine learning offers a powerful framework with natural applications in scientific fields such as chemistry, biology and material sciences. By representing data as a graph, we encode the prior knowledge that the data is composed of a set of entitie ...

EPFL2023

Maximum Independent Set: Self-Training through Dynamic Programming

Volkan Cevher, Grigorios Chrysos, Efstratios Panteleimon Skoulakis

This work presents a graph neural network (GNN) framework for solving the maximum independent set (MIS) problem, inspired by dynamic programming (DP). Specifically, given a graph, we propose a DP-like recursive algorithm based on GNNs that firstly construc ...

2023

Understanding the role of Hubbard corrections in the rhombohedral phase of BaTiO3

Nicola Marzari, Iurii Timrov, Michele Kotiuga, Lorenzo Bastonero

We present a first-principles study of the low-temperature rhombohedral phase of BaTiO3 using Hubbardcorrected density-functional theory. By employing density-functional perturbation theory, we compute the onsite Hubbard U for Ti(3d) states and the intersi ...

College Pk2023

Generalised Implicit Neural Representations

Pierre Vandergheynst

We consider the problem of learning implicit neural representations (INRs) for signals on non-Euclidean domains. In the Euclidean case, INRs are trained on a discrete sampling of a signal over a regular lattice. Here, we assume that the continuous signal e ...

2022

Reduced representations of complexes, signals, and multifiltrations

Celia Camille Hacker

The field of computational topology has developed many powerful tools to describe the shape of data, offering an alternative point of view from classical statistics. This results in a variety of complex structures that are not always directly amenable for ...

EPFL2022

Reduced order modelling of nonaffine problems on parameterized NURBS multipatch geometries

Annalisa Buffa, Pablo Antolin Sanchez, Margarita Chasapi

This contribution explores the combined capabilities of reduced basis methods and IsoGeometric Analysis (IGA) in the context of parameterized partial differential equations. The introduction of IGA enables a unified simulation framework based on a single g ...

2022

Relative, local and global dimension in complex networks

Alexis Arnaudon

Dimension is a fundamental property of objects and the space in which they are embedded. Yet ideal notions of dimension, as in Euclidean spaces, do not always translate to physical spaces, which can be constrained by boundaries and distorted by inhomogenei ...

NATURE PORTFOLIO2022

The power of adaptivity in source identification with time queries on the path

Patrick Thiran, Gergely Odor, Victor Cyril L Lecomte

We study the problem of identifying the source of a stochastic diffusion process spreading on a graph based on the arrival times of the diffusion at a few queried nodes. In a graph

G=(V,E)

, an unknown source node

v^* \in V

is drawn uniformly at random, ...

2022

GeoNeRF: Generalizing NeRF with Geometry Priors

François Fleuret

We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cas ...

IEEE COMPUTER SOC2022

Graph-Based vs Depth-Based Data Representation for Multiview Images

Graph Chatbot

Chat with Graph Search

A full characterization of invariant embeddability of unimodular planar graphs

Equivariant Neural Architectures for Representing and Generating Graphs

Maximum Independent Set: Self-Training through Dynamic Programming

Understanding the role of Hubbard corrections in the rhombohedral phase of BaTiO3

Generalised Implicit Neural Representations

Reduced representations of complexes, signals, and multifiltrations

Reduced order modelling of nonaffine problems on parameterized NURBS multipatch geometries

Relative, local and global dimension in complex networks

The power of adaptivity in source identification with time queries on the path

GeoNeRF: Generalizing NeRF with Geometry Priors

Equivariant Neural Architectures for Representing and Generating Graphs

Reduced representations of complexes, signals, and multifiltrations

Maximum Independent Set: Self-Training through Dynamic Programming

Generalised Implicit Neural Representations

Understanding the role of Hubbard corrections in the rhombohedral phase of BaTiO3

Reduced order modelling of nonaffine problems on parameterized NURBS multipatch geometries

The power of adaptivity in source identification with time queries on the path

Relative, local and global dimension in complex networks

GeoNeRF: Generalizing NeRF with Geometry Priors

A full characterization of invariant embeddability of unimodular planar graphs