DC3DO: Diffusion Classifier for 3D Objects

1 code implementation • 13 Aug 2024 • Nursena Koprucu, Meher Shashwat Nigam, Shicheng Xu, Biruk Abere, Gabriele Dominici, Andrew Rodriguez, Sharvaree Vadgam, Berfin Inal, Alberto Tono

Inspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification.

3D Object Classification Classification +3

3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models

no code implementations • 1 Dec 2022 • Gimin Nam, Mariem Khlifi, Andrew Rodriguez, Alberto Tono, Linqi Zhou, Paul Guerrero

We propose a diffusion model for neural implicit representations of 3D shapes that operates in the latent space of an auto-decoder.

3D Generation 3D Shape Generation +4

Vitruvio: 3D Building Meshes via Single Perspective Sketches

1 code implementation • 24 Oct 2022 • Alberto Tono, Heyaojing Huang, Ashwin Agrawal, Martin Fischer

If previous state-of-the-art (SOTA) data-driven methods for single view reconstruction (SVR) showed outstanding results in the reconstruction process from a single image or sketch, they lacked specific applications, analysis, and experiments in the AEC.

Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture

1 code implementation • 26 Apr 2021 • Stanislava Fedorova, Alberto Tono, Meher Shashwat Nigam, Jiayao Zhang, Amirhossein Ahmadnia, Cecilia Bolognesi, Dominik L. Michels

The variety of annotations, the flexibility to customize the generated building and dataset parameters make this framework suitable for multiple deep learning tasks, including geometric deep learning that requires direct 3D supervision.

Deep Learning Synthetic Data Generation