no code implementations • 20 Mar 2024 • Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Daniel Duckworth, Rama Gosula, Keisuke Tateno, John Bates, Dominik Kaeser, Federico Tombari
First, we use radiance fields as a prior and supervision signal for optimizing point-based scene representations, leading to improved quality and more robust optimization.
no code implementations • 20 Dec 2023 • Fangjinhua Wang, Marie-Julie Rakotosaona, Michael Niemeyer, Richard Szeliski, Marc Pollefeys, Federico Tombari
In this work, we propose UniSDF, a general purpose 3D reconstruction method that can reconstruct large complex scenes with reflections.
1 code implementation • ICCV 2023 • Yichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona, Patrick Rim, Federico Tombari, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan
However, given that objects occupy only a small part of a scene, finding dense candidates and generating dense representations is noisy and inefficient.
no code implementations • 16 Mar 2023 • Marie-Julie Rakotosaona, Fabian Manhardt, Diego Martin Arroyo, Michael Niemeyer, Abhijit Kundu, Federico Tombari
Obtaining 3D meshes from neural radiance fields still remains an open challenge since NeRFs are optimized for view synthesis, not enforcing an accurate underlying geometry on the radiance field.
1 code implementation • CVPR 2023 • Prune Truong, Marie-Julie Rakotosaona, Fabian Manhardt, Federico Tombari
Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views.
1 code implementation • CVPR 2023 • Dario Pavllo, David Joseph Tan, Marie-Julie Rakotosaona, Federico Tombari
Neural Radiance Fields (NeRF) coupled with GANs represent a promising direction in the area of 3D reconstruction from a single view, owing to their ability to efficiently model arbitrary topologies.
1 code implementation • 22 Sep 2021 • Marie-Julie Rakotosaona, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov, Paul Guerrero
Our method builds on the result that any 2D triangulation can be achieved by a suitably perturbed weighted Delaunay triangulation.
1 code implementation • CVPR 2021 • Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov
We leverage the properties of 2D Delaunay triangulations to construct a mesh from manifold surface elements.
2 code implementations • NeurIPS 2020 • Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi, Maks Ovsjanikov
However, instead of using the Laplace-Beltrami eigenfunctions as done in virtually all previous works in this domain, we demonstrate that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings.
Ranked #7 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)
1 code implementation • ECCV 2020 • Marie-Julie Rakotosaona, Maks Ovsjanikov
We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties.
1 code implementation • 27 Jun 2019 • Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, Maks Ovsjanikov
We present a novel rotation invariant architecture operating directly on point cloud data.
1 code implementation • ICCV 2019 • Ruqi Huang, Marie-Julie Rakotosaona, Panos Achlioptas, Leonidas Guibas, Maks Ovsjanikov
This paper proposes a learning-based framework for reconstructing 3D shapes from functional operators, compactly encoded as small-sized matrices.
1 code implementation • 4 Jan 2019 • Marie-Julie Rakotosaona, Vittorio La Barbera, Paul Guerrero, Niloy J. Mitra, Maks Ovsjanikov
Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers.