Recovering facial reflectance and geometry from multi-view images

While the problem of estimating shapes and diffuse reflectances of human faces from images has been extensively studied, there is relatively less work done on recovering the specular albedo. This paper presents a lightweight solution for inferring photorealistic facial reflectance and geometry. Our...

Full description

Bibliographic Details
Main Authors: Song, Guoxian, Zheng, Jianmin, Cai, Jianfei, Cham, Tat-Jen
Other Authors: School of Computer Science and Engineering
Format: Journal Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172643
_version_ 1826112512736624640
author Song, Guoxian
Zheng, Jianmin
Cai, Jianfei
Cham, Tat-Jen
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Song, Guoxian
Zheng, Jianmin
Cai, Jianfei
Cham, Tat-Jen
author_sort Song, Guoxian
collection NTU
description While the problem of estimating shapes and diffuse reflectances of human faces from images has been extensively studied, there is relatively less work done on recovering the specular albedo. This paper presents a lightweight solution for inferring photorealistic facial reflectance and geometry. Our system processes video streams from two views of a subject, and outputs two reflectance maps for diffuse and specular albedos, as well as a vector map of surface normals. A model-based optimization approach is used, consisting of the three stages of multi-view face model fitting, facial reflectance inference and facial geometry refinement. Our approach is based on a novel formulation built upon the 3D morphable model (3DMM) for representing 3D textured faces in conjunction with the Blinn-Phong reflection model. It has the advantage of requiring only a simple setup with two video streams, and is able to exploit the interaction between the diffuse and specular reflections across multiple views as well as time frames. As a result, the method is able to reliably recover high-fidelity facial reflectance and geometry, which facilitates various applications such as generating photorealistic facial images under new viewpoints or illumination conditions.
first_indexed 2024-10-01T03:08:16Z
format Journal Article
id ntu-10356/172643
institution Nanyang Technological University
language English
last_indexed 2024-10-01T03:08:16Z
publishDate 2023
record_format dspace
spelling ntu-10356/1726432023-12-19T01:23:12Z Recovering facial reflectance and geometry from multi-view images Song, Guoxian Zheng, Jianmin Cai, Jianfei Cham, Tat-Jen School of Computer Science and Engineering Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision 3D Facial Reconstruction Specular Estimation While the problem of estimating shapes and diffuse reflectances of human faces from images has been extensively studied, there is relatively less work done on recovering the specular albedo. This paper presents a lightweight solution for inferring photorealistic facial reflectance and geometry. Our system processes video streams from two views of a subject, and outputs two reflectance maps for diffuse and specular albedos, as well as a vector map of surface normals. A model-based optimization approach is used, consisting of the three stages of multi-view face model fitting, facial reflectance inference and facial geometry refinement. Our approach is based on a novel formulation built upon the 3D morphable model (3DMM) for representing 3D textured faces in conjunction with the Blinn-Phong reflection model. It has the advantage of requiring only a simple setup with two video streams, and is able to exploit the interaction between the diffuse and specular reflections across multiple views as well as time frames. As a result, the method is able to reliably recover high-fidelity facial reflectance and geometry, which facilitates various applications such as generating photorealistic facial images under new viewpoints or illumination conditions. This research is supported by Singtel Cognitive and Artificial Intelligence Lab for Enterprises at NTU. 2023-12-19T01:23:12Z 2023-12-19T01:23:12Z 2020 Journal Article Song, G., Zheng, J., Cai, J. & Cham, T. (2020). Recovering facial reflectance and geometry from multi-view images. Image and Vision Computing, 96, 103897-. https://dx.doi.org/10.1016/j.imavis.2020.103897 0262-8856 https://hdl.handle.net/10356/172643 10.1016/j.imavis.2020.103897 2-s2.0-85081129546 96 103897 en Image and Vision Computing © 2020 Elsevier B.V. All rights reserved.
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
3D Facial Reconstruction
Specular Estimation
Song, Guoxian
Zheng, Jianmin
Cai, Jianfei
Cham, Tat-Jen
Recovering facial reflectance and geometry from multi-view images
title Recovering facial reflectance and geometry from multi-view images
title_full Recovering facial reflectance and geometry from multi-view images
title_fullStr Recovering facial reflectance and geometry from multi-view images
title_full_unstemmed Recovering facial reflectance and geometry from multi-view images
title_short Recovering facial reflectance and geometry from multi-view images
title_sort recovering facial reflectance and geometry from multi view images
topic Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
3D Facial Reconstruction
Specular Estimation
url https://hdl.handle.net/10356/172643
work_keys_str_mv AT songguoxian recoveringfacialreflectanceandgeometryfrommultiviewimages
AT zhengjianmin recoveringfacialreflectanceandgeometryfrommultiviewimages
AT caijianfei recoveringfacialreflectanceandgeometryfrommultiviewimages
AT chamtatjen recoveringfacialreflectanceandgeometryfrommultiviewimages