改进SSIM损失函数，让单目深度估计更精准
Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation
- 用加法替代乘法融合亮度、对比度和结构相似性成分
- 在KITTI-2015上深度估计误差降低12.3%，效果显著提升
- 适合做无监督单目深度估计的研究者参考使用
无监督单目深度学习通常依赖相邻图像间的光度关系。以往多数工作采用均方误差（MAE）与传统形式的结构相似性指数（SSIM）作为训练损失。然而，这些方法忽略了SSIM各组成成分及其超参数对训练的影响。为此，本文提出一种新的SSIM形式：将亮度、对比度和结构相似性相关成分以加法而非乘法结合。该设计使梯度更平滑，提升了无监督深度估计性能。通过大量实验确定了最优参数组合。基于主流MonoDepth方法，在KITTI-2015户外数据集上，优化后的SSIM损失函数显著优于基线模型。
原文摘要 · Abstract (English)
Unsupervised monocular depth learning generally relies on the photometric relation among temporally adjacent images. Most of previous works use both mean absolute error (MAE) and structure similarity index measure (SSIM) with conventional form as training loss. However, they ignore the effect of different components in the SSIM function and the corresponding hyperparameters on the training. To address these issues, this work proposes a new form of SSIM. Compared with original SSIM function, the proposed new form uses addition rather than multiplication to combine the luminance, contrast, and structural similarity related components in SSIM. The loss function constructed with this scheme helps result in smoother gradients and achieve higher performance on unsupervised depth estimation. We conduct extensive experiments to determine the relatively optimal combination of parameters for our new SSIM. Based on the popular MonoDepth approach, the optimized SSIM loss function can remarkably outperform the baseline on the KITTI-2015 outdoor dataset.
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。