This paper proposes a new depth completion method based on multi-view improved monitored distillation to generate more accurate depth maps. Based on the state-of-the-art depth completion method named ensemble distillation, we introduce an existing stereo-based model as a teacher model to improve ensemble distillation accuracy and generate a more accurate student model in training by avoiding inherent error modes of completion-based teachers as well as minimizing the reconstruction error for a given image. We also leverage multi-view depth consistency and multi-scale minimum reprojection to provide self-supervised information. These methods use the existing structure constraints to yield supervised signals for student model training without great expense on gathering ground truth information of depth. Our extensive experimental evaluation demonstrates that our proposed method can effectively improve the accuracy of baseline method of monitored distillation.

翻译：本文提出了一种基于多视角改进监测蒸馏的深度补全新方法，以生成更精确的深度图。基于名为集成蒸馏的深度补全最优方法，我们引入现有的立体视觉模型作为教师模型，通过避免基于补全的教师模型固有的误差模式，并最小化给定图像的重建误差，从而提高集成蒸馏精度，并在训练中生成更精确的学生模型。我们还利用多视角深度一致性和多尺度最小重投影提供自监督信息。这些方法利用现有结构约束为学生模型训练生成监督信号，而无需花费大量成本收集深度真值数据。广泛的实验评估表明，所提方法能够有效提升监测蒸馏基线方法的精度。