3 Dimensional Dense Reconstruction: A Review of Algorithms and Dataset

TL;DR

This paper reviews classical and deep learning methods for 3D dense reconstruction from 2D images, discussing datasets, performance, and the advantages and disadvantages of each approach.

Contribution

It provides a comprehensive overview of existing algorithms and datasets for 3D dense reconstruction, highlighting recent deep learning advancements.

Findings

Deep learning methods show promising results on reconstruction datasets.

Classical geometric and optical models remain foundational in the field.

Datasets are crucial for training and evaluating deep learning-based reconstruction algorithms.

Abstract

3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This work systematically introduces classical methods of 3D dense reconstruction based on geometric and optical models, as well as methods based on deep learning. It also introduces datasets for deep learning and the performance and advantages and disadvantages demonstrated by deep learning methods on these datasets.