# Visual Localization Using Semantic Segmentation and Depth Prediction

Source: [Visual Localization Using Semantic Segmentation and Depth Prediction](<https://www.sota2.com/research/paper/68fa679a1e209131cea17617>)

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

Data updated: 2025-10-27T06:02:46.151Z

Authors: Huanhuan Fan, Yuhao Zhou, Ang Li, Shuang Gao, Jijunnan Li, Yandong Guo

Published: 2020-05-25T04:55:27.000Z

## Abstract

In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. We apply semantic consistency evaluation to rank the image retrieval results and a practical clustering technique to reject estimation outliers. In addition, we demonstrate a substantial performance boost achieved with a combination of multiple feature extractors. Furthermore, by using depth prediction with a deep neural network, we show that a significant amount of falsely matched keypoints are identified and eliminated. The proposed pipeline outperforms most of the existing approaches at the Long-Term Visual Localization benchmark 2020.

## 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/2005.11922>)

[PDF](<https://arxiv.org/pdf/2005.11922.pdf>)