We present a fine-tuning method to improve the appearance of 3D geometries reconstructed from single images. We leverage advances in monocular depth estimation to obtain disparity maps and present a novel approach to transforming 2D normalized disparity maps into 3D point clouds by using shape priors to solve an optimization on the relevant camera parameters. After creating a 3D point cloud from disparity, we introduce a method to combine the new point cloud with existing information to form a more faithful and detailed final geometry. We demonstrate the efficacy of our approach with multiple experiments on both synthetic and real images.
@article{arxiv.2207.00182,
title = {Recovering Detail in 3D Shapes Using Disparity Maps},
author = {Marissa Ramirez de Chanlatte and Matheus Gadelha and Thibault Groueix and Radomir Mech},
journal= {arXiv preprint arXiv:2207.00182},
year = {2022}
}