会议论文

Ni, BB

英文

COMPUTER VISION - ECCV 2024, PT XXVII

0302-9743

2025

15085

340-356

18th European Conference on Computer Vision (ECCV)

Lecture Notes in Computer Science

SEP 29-OCT 04, 2024

Milan, ITALY

[Jin, Qiaoqiao;Chen, Xuanhong;Shi, Rui;Zheng, Yucheng;Zhu, Yupeng;Ni, Bingbing] Shanghai Jiao Tong Univ, Shanghai 200240, Peoples R China.^[Jin, Meiguang;Chen, Ying] Alibaba Grp, Hangzhou, Peoples R China.^[Chen, Xuanhong] USC SJTU, Inst Cultural & Creat Ind, Shanghai, Peoples R China.

Ricci, E Leonardis, A Roth, S Russakovsky, O Sattler, T Varol, G

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

978-3-031-73382-6; 978-3-031-73383-3

10.1007/978-3-031-73383-3_20

National Science Foundation of China [U20B2072, 61976137]; SJTU Medical Engineering Cross Research [YG2021ZD18]

本校为其他机构

Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet they grapple with the challenges of inaccurate supervision (e.g., face misalignment) and sophisticated facial prompts (including face parsing, and landmark detection). These challenges prohibit low-cost deployment of facial makeup models, especially on mobile devices. To solve above problems, we propose a brand-new learning paradigm, termed "Data Amplify Learning (DAL)," alongside a compact makeup model named "TinyBeauty." The core idea of DAL lies in employing a Diffusion-based Data Amplifier (DDA) to "amplify"...