用半监督方法仅需6.7%标注数据，实现接近全监督的HDR图像重建效果
Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking
- 通过教师模型生成伪标签，学生模型在不确定区域被遮蔽后学习
- 仅用6.7%真实HDR标签即达到与全监督方法相当的性能
- 基于像素和块级不确定性掩码，有效避免伪标签中的错误传播
从低动态范围（LDR）序列重建高动态范围（HDR）图像在计算摄影中至关重要。基于学习的方法虽取得显著进展，但依赖大量成对的LDR-HDR数据，而此类数据难以获取。为此，本文探索注释高效的HDR重建：如何在极少真实HDR标签下实现良好性能。采用半监督学习框架，教师模型为无标签样本生成伪HDR标签，学生模型从中学习。为克服因伪标签含误差导致的确认偏见问题，提出基于不确定性的像素与块级掩码机制，剔除不可靠区域，仅保留可信部分供学生学习。实验表明，该方法不仅优于现有注释高效算法，且仅使用6.7%的真值标签即可媲美最新全监督方法。
原文摘要 · Abstract (English)
Reconstructing high dynamic range (HDR) images from low dynamic range (LDR) bursts plays an essential role in the computational photography. Impressive progress has been achieved by learning-based algorithms which require LDR-HDR image pairs. However, these pairs are hard to obtain, which motivates researchers to delve into the problem of annotation-efficient HDR image reconstructing: how to achieve comparable performance with limited HDR ground truths (GTs). This work attempts to address this problem from the view of semi-supervised learning where a teacher model generates pseudo HDR GTs for the LDR samples without GTs and a student model learns from pseudo GTs. Nevertheless, the confirmation bias, i.e., the student may learn from the artifacts in pseudo HDR GTs, presents an impediment. To remove this impediment, an uncertainty-based masking process is proposed to discard unreliable parts of pseudo GTs at both pixel and patch levels, then the trusted areas can be learned from by the student. With this novel masking process, our semi-supervised HDR reconstructing method not only outperforms previous annotation-efficient algorithms, but also achieves comparable performance with up-to-date fully-supervised methods by using only 6.7% HDR GTs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。