Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking

TL;DR

This paper introduces a semi-supervised method for HDR image reconstruction that uses an uncertainty-based masking process to effectively leverage limited HDR ground truths, achieving high performance with minimal labeled data.

Contribution

The paper proposes a novel uncertainty-based masking technique to improve semi-supervised HDR reconstruction, reducing reliance on extensive HDR ground truth data.

Findings

Outperforms previous annotation-efficient algorithms.

Achieves comparable performance to fully-supervised methods with only 6.7% HDR GTs.

Effective removal of artifacts through uncertainty-based masking.

Abstract

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.