Video-Based Stabilized 3D Face Alignment Using Temporal Multi-Discrimination
- Authors
- Lee, Seongmin; Yoon, Hyunse; Kang, Jiwoo; Kim, Jungsu; Son, Jiwan; Huh, Jungwoo; Lee, Sanghoon
- Issue Date
- Sep-2023
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- 3D face alignment; stabilized face alignment; temporal discrimination
- Citation
- 2023 IEEE 25th International Workshop on Multimedia Signal Processing, MMSP 2023, v.2023, pp 1 - 6
- Pages
- 6
- Journal Title
- 2023 IEEE 25th International Workshop on Multimedia Signal Processing, MMSP 2023
- Volume
- 2023
- Start Page
- 1
- End Page
- 6
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/159618
- DOI
- 10.1109/MMSP59012.2023.10337645
- ISSN
- 2163-3517
2473-3628
- Abstract
- Existing 3D face alignment primarily aim to achieve accurate face alignment result for a static facial image. While these methods have strong alignment performance under large poses, occlusion, and extreme lighting conditions, they often result in trembling artifacts in video-based sequential 3D face alignment. Reducing temporal misalignment remains a challenging task because a single misaligned frame can propagate errors to other frames along the temporal axis. To address this issue, we propose a novel temporal discriminating scheme that learns the distribution gap between the face alignment results and ground truth face animation. By leveraging the discrimination results as a guide, the proposed method can effectively align the 3D faces to the input video by reducing temporal trembling artifacts. To effectively learn the distribution gap, we introduce a multi-discriminating scheme that separately discriminates facial animation based on identity and expression changes. It enables the proposed method to produce a stabilized alignment result, especially in dynamic and fast movement. Through extensive experiments in both qualitative and quantitative evaluations, it is confirmed that our method outperforms state-of-the-art 3D face alignment methods by animating stabilized results in the video.
- Files in This Item
-
Go to Link
- Appears in
Collections - ICT융합공학부 > IT공학전공 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.