# FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation

Source: [FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation](<https://www.sota2.com/research/paper/68fa6e811e209131cea40663>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:20:27.891Z

Authors: Junyu Zhu, Lina Liu, Yong Liu, Wanlong Li, Feng Wen, Hongbo Zhang

Published: 2023-01-20T04:02:13.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.08414>)

[PDF](<https://arxiv.org/pdf/2301.08414.pdf>)
