3D

We worked on three main topics related to 3D:

• reconstructing 3D models from multiple (historical) photographs
• reconstructing 3D models from a single (historical) photographs
• mining 3D data for repetitive elements.

We have made several important contribution to 3D data representations with deep learning, that we think are key steps toward these goals. The two main contributions could be summarized as (i) focussing on describing 3D deformations (ii) analyzing data by learning to synthesize.

Publications:

Learning elementary structures for 3D shape generation and matching, Thé Deprelle, Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell and Mathieu Aubry, NeurIPS 2019, PDF, Project page

3D-CODED : 3D Correspondences by Deep Deformation, Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell and Mathieu Aubry, ECCV 2018, PDF, Project page

AtlasNet: A Papier-Mâché Approach to Learning Surface Generation, Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell and Mathieu Aubry, CVPR 2018, PDF, Project page

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
T. Monnier, M. Fisher, A. Efros, M. Aubry
ECCV 2022
Download pdf | View project web page

NeuralWarp: Improving neural implicit surfaces geometry with patch warping
F. Darmon, B. Bascle, J.-C. Devaux, P. Monasse, M. Aubry
CVPR 2022
Download pdf | View project web page