Zheng Yuanfeng, Yan Yuchen, Jiang Hao
School of Electronic Information, Wuhan University, Wuhan 430072, China.
Sensors (Basel). 2024 May 13;24(10):3090. doi: 10.3390/s24103090.
Despite recent notable advancements in highlight image restoration techniques, the dearth of annotated data and the lightweight deployment of highlight removal networks pose significant impediments to further advancements in the field. In this paper, to the best of our knowledge, we first propose a semi-supervised learning paradigm for highlight removal, merging the fusion version of a teacher-student model and a generative adversarial network, featuring a lightweight network architecture. Initially, we establish a dependable repository to house optimal predictions as pseudo ground truth through empirical analyses guided by the most reliable No-Reference Image Quality Assessment (NR-IQA) method. This method serves to assess rigorously the quality of model predictions. Subsequently, addressing concerns regarding confirmation bias, we integrate contrastive regularization into the framework to curtail the risk of overfitting on inaccurate labels. Finally, we introduce a comprehensive feature aggregation module and an extensive attention mechanism within the generative network, considering a balance between network performance and computational efficiency. Our experimental evaluations encompass comprehensive assessments on both full-reference and non-reference highlight benchmarks. The results demonstrate conclusively the substantive quantitative and qualitative enhancements achieved by our proposed algorithm in comparison to state-of-the-art methodologies.
尽管高光图像恢复技术最近取得了显著进展，但标注数据的匮乏以及高光去除网络的轻量级部署，对该领域的进一步发展构成了重大障碍。在本文中，据我们所知，我们首次提出了一种用于高光去除的半监督学习范式，融合了师生模型的融合版本和生成对抗网络，具有轻量级网络架构。首先，我们通过由最可靠的无参考图像质量评估（NR-IQA）方法指导的实证分析，建立了一个可靠的存储库，将最优预测作为伪真值存储起来。该方法用于严格评估模型预测的质量。随后，针对确认偏差问题，我们将对比正则化集成到框架中，以降低在不准确标签上过度拟合的风险。最后，考虑到网络性能和计算效率之间的平衡，我们在生成网络中引入了一个综合特征聚合模块和一个广泛的注意力机制。我们的实验评估包括对全参考和无参考高光基准的全面评估。结果确凿地表明，与现有最先进方法相比，我们提出的算法在定量和定性方面都取得了实质性的提升。
