From Flat to Spatial: Comparison of 4 methods constructing 3D, 2 and 1/2D Models from 2D Plans with neural networks

TL;DR

This paper compares four advanced neural network-based methods for converting 2D architectural plans and images into detailed 3D, 2.5D, and 1.5D models, highlighting their effectiveness in rapid visualization and design iteration.

Contribution

It provides a comprehensive evaluation of four novel methods for 3D model generation from 2D inputs, emphasizing their applicability in architecture and visualization.

Findings

All methods improve speed of 3D model creation.

Each method offers unique advantages in accuracy and texture fidelity.

The study guides selection of methods based on project needs.

Abstract

In the field of architecture, the conversion of single images into 2 and 1/2D and 3D meshes is a promising technology that enhances design visualization and efficiency. This paper evaluates four innovative methods: "One-2-3-45," "CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model," "Instant Mesh," and "Image-to-Mesh." These methods are at the forefront of this technology, focusing on their applicability in architectural design and visualization. They streamline the creation of 3D architectural models, enabling rapid prototyping and detailed visualization from minimal initial inputs, such as photographs or simple sketches.One-2-3-45 leverages a diffusion-based approach to generate multi-view reconstructions, ensuring high geometric fidelity and texture quality. CRM utilizes a convolutional network to integrate geometric priors into its architecture, producing detailed and textured meshes quickly and efficiently. Instant Mesh combines the strengths of multi-view diffusion and sparse-view models to offer speed and scalability, suitable for diverse architectural projects. Image-to-Mesh leverages a generative adversarial network (GAN) to produce 3D meshes from single images, focusing on maintaining high texture fidelity and geometric accuracy by incorporating image and depth map data into its training process. It uses a hybrid approach that combines voxel-based representations with surface reconstruction techniques to ensure detailed and realistic 3D models.This comparative study highlights each method's contribution to reducing design cycle times, improving accuracy, and enabling flexible adaptations to various architectural styles and requirements. By providing architects with powerful tools for rapid visualization and iteration, these advancements in 3D mesh generation are set to revolutionize architectural practices.