SEMNet: A Simple and Efficient MLP-based Network for 3D Face Point Clouds Landmarks Localization

Author:

Lei Mingyang1,Song Hong1,Fu Tianyu1,Xiao Deqiang1,Ai Danni1,Fan Jingfan1,Yang Yifei1,Gu Ying1,Yang Jian1

Affiliation:

1. Beijing Institute of Technology

Abstract

Abstract

Accurately localizing landmarks on 3D faces is critical for various applications, such as expression recognition, facial surgery navigation, and lip shape analysis. Existing landmarks localization methods generally contain complex calculation processes, which may affecting the efficiency. To address this problem, we propose a Simple and Efficient MLP-based Network (SEMNet) for landmarks localization. We first design a lightweight enhanced geometric affine module to adaptively transform point features in local region, for improving performance and generalization. Then, to fully utilize the rotation information of the face, a rotation constraint auxiliary branch is introduced for assisting in locating landmarks. In addition, to generate more accurate results, we propose a residual graph convolution discriminator to distinguish predicted locations from real face point clouds locations. Experimental results on two public datasets (FRGC v2 and Bosphorus) show that our method achieves high accuracy and efficiency compared to state-of-the-art methods. The project page is available at https://github.com/leimingyangde/SEMNet.

Publisher

Springer Science and Business Media LLC

Reference39 articles.

1. EAPT: Efficient Attention Pyramid Transformer for Image Processing;Lin X;IEEE Trans. Multim,2023

2. MNGNAS: Distilling Adaptive Combination of Multiple Searched Networks for One-Shot Neural Architecture Search;Chen Z;IEEE Trans. Pattern Anal. Mach. Intell.,2023

3. PhotoHelper: Portrait Photographing Guidance Via Deep Feature Retrieval and Fusion;Jiang N;IEEE Trans. Multim.,2023

4. Improving Video Temporal Consistency via Broad Learning System;Sheng B;IEEE Trans. Cybern,2022

5. Automatic Detection and Classification System of Domestic Waste via Multimodel Cascaded Convolutional Neural Network;Li J;IEEE Trans. Ind. Informatics,2022

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3