SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders

Qingsen Yan, Song Zhang, Weiye Chen, Hao Tang, Yu Zhu, Jinqiu Sun, Luc Van Gool, Yanning Zhang

科研成果: 书/报告/会议事项章节会议稿件同行评审

15 引用 (Scopus)

摘要

Generating a high-quality High Dynamic Range (HDR) image from dynamic scenes has recently been extensively studied by exploiting Deep Neural Networks (DNNs). Most DNNs-based methods require a large amount of training data with ground truth, requiring tedious and time-consuming work. Few-shot HDR imaging aims to generate satisfactory images with limited data. However, it is difficult for modern DNNs to avoid overfitting when trained on only a few images. In this work, we propose a novel semi-supervised approach to realize few-shot HDR imaging via two stages of training, called SSHDR. Unlikely previous methods, directly recovering content and removing ghosts simultaneously, which is hard to achieve optimum, we first generate content of saturated regions with a self-supervised mechanism and then address ghosts via an iterative semi-supervised learning framework. Concretely, considering that saturated regions can be regarded as masking Low Dynamic Range (LDR) input regions, we design a Saturated Mask AutoEncoder (SMAE) to learn a robust feature representation and reconstruct a non-saturated HDR image. We also propose an adaptive pseudo-label selection strategy to pick high-quality HDR pseudo-labels in the second stage to avoid the effect of mislabeled samples. Experiments demonstrate that SSHDR outperforms state-of-the-art methods quantitatively and qualitatively within and across different datasets, achieving appealing HDR visualization with few labeled samples.

源语言英语
主期刊名Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
出版商IEEE Computer Society
5775-5784
页数10
ISBN(电子版)9798350301298
DOI
出版状态已出版 - 2023
活动2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, 加拿大
期限: 18 6月 202322 6月 2023

出版系列

姓名Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2023-June
ISSN(印刷版)1063-6919

会议

会议2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
国家/地区加拿大
Vancouver
时期18/06/2322/06/23

指纹

探究 'SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders' 的科研主题。它们共同构成独一无二的指纹。

引用此