From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
Jin Han Lee, Myung-Kyu Han, Dong Wook Ko and Il Hong Suh Department of Electronics and Computer Engineering, Hanyang University {jinhanlee, mkhan91, pumpblack,
Abstract
Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress with plausible results. The convolutional neural networks are generally composed of two parts: an encoder for dense feature extraction and a decoder for predicting the desired depth. In the encoder-decoder schemes, repeated strided convolution and spatial pooling layers lower the spatial resolution of transitional outputs, and several techniques such as skip connections or multi-layer deconvolutional networks are adopted to recover the original resolution for effective dense prediction.
中文速览
单目深度估计（monocular depth estimation）面临的核心难题是：一张2D图像对应无数种可能的3D场景，天然是病态问题。针对这一挑战，研究者提出了一种新型编解码网络，其关键创新是在解码阶段的多个尺度上引入"局部平面引导层"（Local Planar Guidance，LPG）——该层利用局部平面假设，为每个空间区域估计四维平面系数，再通过光线与平面的交点将其转换为稠密深度线索，从而在1/8、1/4、1/2等不同分辨率下分别产生几何引导，最终拼接融合得到全分辨率的深度预测。在NYU Depth V2和KITTI两个主流基准数据集上的实验表明，该方法以显著优势超越了当时所有已有方法，消融实验也验证了局部平面引导机制的有效性。这项工作的重要意义在于：它为编解码结构中内部特征与最终输出之间建立了更加直接、可解释的几何关联，为后续稠密预测任务提供了新的设计思路。
原文 arXiv:1907.10326;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1907.10326v6