# Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

## TL;DR

This paper surveys recent advances in image-based 3D object reconstruction using deep learning, highlighting methods, architectures, and challenges in reconstructing shapes from RGB images.

## Contribution

It provides a comprehensive overview of deep learning techniques for 3D reconstruction, organizing methods by shape representation, network design, and training strategies.

## Key findings

- Deep learning has significantly improved 3D reconstruction accuracy.
- Various shape representations and network architectures are used.
- Open problems include handling complex scenes and improving generalization.

## Abstract

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural networks (CNN) has attracted increasing interest and demonstrated an impressive performance. Given this new era of rapid evolution, this article provides a comprehensive survey of the recent developments in this field. We focus on the works which use deep learning techniques to estimate the 3D shape of generic objects either from a single or multiple RGB images. We organize the literature based on the shape representations, the network architectures, and the training mechanisms they use. While this survey is intended for methods which reconstruct generic objects, we also review some of the recent works which focus on specific object classes such as human body shapes and faces. We provide an analysis and comparison of the performance of some key papers, summarize some of the open problems in this field, and discuss promising directions for future research.