Conference proceeding
Landmark-based 3D Face Reconstruction from an Arbitrary Number of Unconstrained Images
IEEE International Conference and Workshops on Automatic Face and Gesture Recognition : FG, pp 774-779
01 Jan 2018
Abstract
In this paper, we propose a novel method for reconstructing 3D faces from 2D images. The method is characterized in three aspects. (i) It utilizes only geometric cues in the input images, i.e., 2D facial landmarks. (ii) It works for an arbitrary number of unconstrained images, both single and multiple images. (iii) It can effectively exploit complementary information in multiple images of varying poses and expressions. The method is implemented based on cascaded regression in shape space. We have evaluated the method on three databases and observed from the experimental results that (i) the reconstruction error is reduced as more images of different poses are used, (ii) the proposed method can obtain comparable reconstruction results by using state-of-the-art automated methods to detect the 2D landmarks, and (iii) the proposed method is robust to variations in facial expressions and image qualities.
Metrics
Details
- Title
- Landmark-based 3D Face Reconstruction from an Arbitrary Number of Unconstrained Images
- Creators
- Wan Tian - Chengdu UniversityFeng Liu - Sichuan UniversityQijun Zhao - Sichuan University
- Publication Details
- IEEE International Conference and Workshops on Automatic Face and Gesture Recognition : FG, pp 774-779
- Series
- IEEE International Conference on Automatic Face and Gesture Recognition and Workshops
- Publisher
- IEEE
- Number of pages
- 6
- Grant note
- 2017RZ0016 / Miaozi Key Project in Science and Technology Innovation Program of Sichuan Province, China 2013YQ49087904 / National Key Scientific Instrument and Equipment Development Projects of China; National Key Research & Development Program of China 2017YFB0802300; 2016YFC0801100 / National Key Research and Development Program of China; National Key Research & Development Program of China 61773270 / National Natural Science Foundation of China; National Natural Science Foundation of China (NSFC)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000454996700112
- Scopus ID
- 2-s2.0-85049398138
- Other Identifier
- 991022048714804721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Engineering, Electrical & Electronic