1 code implementation • 28 May 2024 • Donato Crisostomi, Marco Fumero, Daniele Baieri, Florian Bernard, Emanuele Rodolà
In this paper, we present a novel data-free method for merging neural networks in weight space.
no code implementations • 21 May 2024 • Daniele Baieri, Filippo Maggioli, Zorah Lähner, Simone Melzi, Emanuele Rodolà
Then, we apply this representation in the setting of handle-guided deformation: we introduce two distinct pipelines, which make use of 3D neural fields to compute As-Rigid-As-Possible deformations of both high-resolution meshes and neural fields under a given set of constraints.
no code implementations • 8 Mar 2024 • Francesco Palandra, Andrea Sanchietti, Daniele Baieri, Emanuele Rodolà
We present GSEdit, a pipeline for text-guided 3D object editing based on Gaussian Splatting models.
no code implementations • 17 Mar 2023 • Daniele Baieri, Stefano Esposito, Filippo Maggioli, Emanuele Rodolà
Representing 3D surfaces as level sets of continuous functions over $\mathbb{R}^3$ is the common denominator of neural implicit representations, which recently enabled remarkable progress in geometric deep learning and computer vision tasks.
no code implementations • 22 Jun 2022 • Stefano Esposito, Daniele Baieri, Stefan Zellmann, André Hinkenjann, Emanuele Rodolà
NeRF-based techniques fit wide and deep multi-layer perceptrons (MLPs) to a continuous radiance field that can be rendered from any unseen viewpoint.