Monocular depth estimation has drawn widespread attention from the vision
community due to its broad applications. In this paper, we propose a novel
physics (geometry)-driven deep learning framework for monocular depth
estimation by assuming that 3D scenes are constituted by piece-wise planes.
Particularly, we introduce a new normal-distance head that outputs pixel-level
surface normal and plane-to-origin distance for deriving depth at each
position. Meanwhile, the normal and distance are regularized by a developed
plane-aware consistency constraint. We further integrate an additional depth
head to improve the robustness of the proposed framework. To fully exploit the
strengths of these two heads, we develop an effective contrastive iterative
refinement module that refines depth in a complementary manner according to the
depth uncertainty. Extensive experiments indicate that the proposed method
exceeds previous state-of-the-art competitors on the NYU-Depth-v2, KITTI and
SUN RGB-D datasets. Notably, it ranks 1st among all submissions on the KITTI
depth prediction online benchmark at the submission time.

基于物理驱动的深度学习框架用于单目深度估计，通过假设 3D 场景由分段平面组成，提出了一种新的正常 - 距离头来推导每个位置的深度，同时，通过开发的面感知一致性约束对正常和距离进行规范化，并引入了额外的深度头来改善框架的鲁棒性，利用有效的对比迭代细化模块根据深度的不确定性互补地对深度进行精细化改进，实验证明该方法在 NYU-Depth-v2、KITTI 和 SUN RGB-D 数据集上超过了现有的最先进竞争方法，值得注意的是，它在 KITTI 深度预测在线基准测试中的提交时间中排名第一。