Over the past few years, self-supervised monocular depth estimation that does not depend on ground-truth during the training phase has received widespread attention. Most efforts focus on designing different types of network architectures and loss functions or handling edge cases, e.g., occlusion and dynamic objects. In this work, we introduce a novel self-supervised depth estimation framework, dubbed MonoDiffusion, by formulating it as an iterative denoising process. Because the depth ground-truth is unavailable in the training phase, we develop a pseudo ground-truth diffusion process to assist the diffusion in MonoDiffusion. The pseudo ground-truth diffusion gradually adds noise to the depth map generated by a pre-trained teacher model. Moreover,the teacher model allows applying a distillation loss to guide the denoised depth. Further, we develop a masked visual condition mechanism to enhance the denoising ability of model. Extensive experiments are conducted on the KITTI and Make3D datasets and the proposed MonoDiffusion outperforms prior state-of-the-art competitors. The source code will be available at https://github.com/ShuweiShao/MonoDiffusion.

翻译：近年来，不依赖训练阶段真实标注的自监督单目深度估计方法受到广泛关注。现有研究主要聚焦于设计不同类型的网络架构与损失函数，或处理遮挡、动态物体等边缘情况。本文提出一种名为MonoDiffusion的新型自监督深度估计框架，通过将其表述为迭代去噪过程实现。由于训练阶段缺乏深度真实值，我们开发了伪真实值扩散机制来辅助MonoDiffusion中的扩散过程。该机制逐步向预训练教师模型生成的深度图添加噪声。此外，教师模型支持应用蒸馏损失指导去噪深度图的生成。进一步，我们设计了掩码视觉条件机制增强模型的去噪能力。在KITTI和Make3D数据集上的大量实验表明，所提出的MonoDiffusion方法优于现有最先进方法。源代码将发布于https://github.com/ShuweiShao/MonoDiffusion。