FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation

TL;DR

FG-Depth introduces a flow-guided framework for unsupervised monocular depth estimation, leveraging pretrained Flow-Net to improve optimization and achieve state-of-the-art results on standard datasets.

Contribution

The paper proposes a novel flow distillation loss and prior flow-based masking to enhance unsupervised depth estimation, overcoming local minima issues in previous methods.

Findings

Achieves state-of-the-art performance on KITTI and NYU-Depth-v2 datasets.

Demonstrates the effectiveness of flow-guided optimization over traditional photometric loss.

Improves training stability and accuracy in monocular depth estimation.

Abstract

The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods. To further improve the performance, recent works mainly focus on designing more complex network structures and exploiting extra supervised information, e.g., semantic segmentation. These methods optimize the models by exploiting the reconstructed relationship between the target and reference images in varying degrees. However, previous methods prove that this image reconstruction optimization is prone to get trapped in local minima. In this paper, our core idea is to guide the optimization with prior knowledge from pretrained Flow-Net. And we show that the bottleneck of unsupervised monocular depth estimation can be broken with our simple but effective framework named FG-Depth. In particular, we propose (i) a flow distillation loss to replace the typical photometric loss that limits the capacity of the model and (ii) a prior flow based mask to remove invalid pixels that bring the noise in training loss. Extensive experiments demonstrate the effectiveness of each component, and our approach achieves state-of-the-art results on both KITTI and NYU-Depth-v2 datasets.