Space and Time Continuous Physics Simulation From Partial Observations

Autor: Steeven, Janny, Madiha, Nadri, Julie, Digne, Christian, Wolf

Modern techniques for physical simulations rely on numerical schemes and mesh-refinement methods to address trade-offs between precision and complexity, but these handcrafted solutions are tedious and require high computational power. Data-driven met

Externí odkaz: http://arxiv.org/abs/2401.09198

Dynamic scene novel view synthesis via deferred spatio-temporal consistency

Autor: Beatrix-Emőke Fülöp-Balogh, Eleanor Tursman, James Tompkin, Julie Digne, Nicolas Bonneel

Publikováno v: Computers & Graphics. 107:220-230

Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint. Both are hard with casual capture and dyn

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3164a33a780529e11fca7d6ffb7ed965
https://doi.org/10.1016/j.cag.2022.07.019

An Analysis and Implementation of a Parallel Ball Pivoting Algorithm

Autor: Julie Digne

Publikováno v: Image Processing On Line, Vol 4, Pp 149-168 (2014)

The problem of surface reconstruction from a set of 3D points given by their coordinates andoriented normals is a difficult problem, which has been tackled with many different approaches.In 1999, Bernardini and colleagues introduced a very elegant an

Externí odkaz: https://doaj.org/article/219541d059664befb79167be547eb557

Gradient Terrain Authoring

Autor: Eric Guérin, Adrien Peytavie, Simon Masnou, Julie Digne, Basile Sauvage, James Gain, Eric Galin

Publikováno v: Computer Graphics Forum
Computer Graphics Forum, 2022, 41 (2), ⟨10.1111/cgf.14460⟩

International audience; Digital terrains are a foundational element in the computer-generated depiction of natural scenes. Given the variety and complexity of real-world landforms, there is a need for authoring solutions that achieve perceptually rea

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4cc12ef9f1d7e94865c92f6a330e5a13
https://hal.science/hal-03577171

Learning to Generate Wasserstein Barycenters

Autor: Julien Lacombe, Julie Digne, Nicolas Courty, Nicolas Bonneel

Publikováno v: Journal of Mathematical Imaging and Vision
Journal of Mathematical Imaging and Vision, 2022, 65, pp.354-370. ⟨10.1007/s10851-022-01121-y⟩
Journal of Mathematical Imaging and Vision, In press, ⟨10.1007/s10851-022-01121-y⟩

Optimal transport is a notoriously difficult problem to solve numerically, with current approaches often remaining intractable for very large scale applications such as those encountered in machine learning. Wasserstein barycenters -- the problem of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ec3510b84fa6355f924c3809702542d9
https://hal.archives-ouvertes.fr/hal-03374452/document