NeuralNetwork Based 3D Surface Reconstruction

TL;DR

This paper introduces a neural network model for 3D surface reconstruction that effectively combines diffuse and specular reflections, enabling accurate surface normal estimation without prior knowledge of lighting conditions.

Contribution

It presents a novel adaptive hybrid-reflectance neural network that considers local surface properties and does not require known illuminant directions for 3D reconstruction.

Findings

Accurate surface normal estimation from 2D images.

Effective reconstruction of 3D facial surfaces.

No need for prior illuminant information.

Abstract

This paper proposes a novel neural-network-based adaptive hybrid-reflectance three-dimensional (3-D) surface reconstruction model. The neural network combines the diffuse and specular components into a hybrid model. The proposed model considers the characteristics of each point and the variant albedo to prevent the reconstructed surface from being distorted. The neural network inputs are the pixel values of the two-dimensional images to be reconstructed. The normal vectors of the surface can then be obtained from the output of the neural network after supervised learning, where the illuminant direction does not have to be known in advance. Finally, the obtained normal vectors can be applied to integration method when reconstructing 3-D objects. Facial images were used for training in the proposed approach