30 citations
- Fabien L. Gandon2 profiles7 · h 36
- Franck Michel3 profiles7 · h 15
- A. Breier3 · h 12
- A. Dorne3 · h 5
- Á. Koszorús3 profiles3 · h 13
- Andrew I. Comport3 · h 1
- Antoine Schnepf3 · h 3
- B. van den Borne2 profiles3 · h 0
- Catherine Faron-Zucker2 profiles3 · h 3
- Célian Ringwald3 · h 3
- D. Hanstorp3 · h 5
- Flavian Vasile3 · h 14
- Laboratoire d'Informatique, Signaux et Systèmes de Sophia AntipolisFR18 papers
- Centre National de la Recherche ScientifiqueFR13 papers
- Université Côte d'AzurFR10 papers
- Institut de Biologie ValroseFR9 papers
- Criteo (France)FR3 papers
- European Organization for Nuclear ResearchCH3 papers
- Institut national de l’information géographique et forestièreFR3 papers
- Institut national de recherche en sciences et technologies du numériqueFR3 papers
- Johannes Gutenberg University MainzDE3 papers
- KU LeuvenBE3 papers
- Laboratoire de Physique des 2 Infinis Irène Joliot-CurieFR3 papers
- Massachusetts Institute of TechnologyUS3 papers
5 papers · 1 filter
Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?
Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi +5
Tri-Planar NeRFs enable the application of powerful 2D vision models for 3D tasks, by representing 3D objects using 2D planar structures. This has made them the prevailing choice t…
Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi +5
While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides red…
Precise spiking motifs in neurobiological and neuromorphic data
Antoine Grimaldi, Amélie Gruel, Camille Besnainou +3
Why do neurons communicate through spikes? By definition, spikes are all-or-none neural events which occur at continuous times. In other words, spikes are on one side binary, exist…
Exploring 3D-aware Latent Spaces for Efficiently Learning Numerous Scenes
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi +5
We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory…
Strong Priority and Determinacy in Timed CCS
Luigi Liquori, Michael Mendler
Building on the standard theory of process algebra with priorities, we identify a new scheduling mechanism, called "constructive reduction" which is designed to capture the essence…