Visual Localization Using Semantic Segmentation and Depth Prediction

2020-05-25 · Huanhuan Fan, Yuhao Zhou, Ang Li, Shuang Gao, Jijunnan Li, Yandong Guo

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.

📄 PDF Abstract BibTeX arXiv:2005.11922

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringDepth EstimationDepth PredictionImage Retrieval Prediction Real-Time Semantic Segmentation Retrieval Semantic Segmentation Visual Localization

Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

2021-04-28 · ICCV 2021 10 · Qin Wang, Dengxin Dai, Lukas Hoyer, Luc van Gool 외

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth e…

Depth Estimation Depth Prediction Domain Adaptation Feature Correlation+3

Learning Geocentric Object Pose in Oblique Monocular Images

2020-07-01 · CVPR 2020 6 · Gordon Christie, Rodrigo Rene Rai Munoz Abujder, Kevin Foster, Shea Hagstrom 외

An object's geocentric pose, defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks usi…

Earth Observation Object object-detection Object Detection+2

Privacy-Preserving Depth-Only Open-Vocabulary 3D Semantic Segmentation Via Uncertainty-Guided Test-Time Optimization

2026-07-01 · Xuying Huang, Sicong Pan, Maren Bennewitz arxiv

Privacy-preserving perception is a critical requirement for deploying 3D scene understanding systems in real-world indoor environments, yet it remains underexplored in open-vocabulary 3D semantic segmentation. Existing m…

3D Semantic Segmentation Scene Understanding

AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models

2026-03-01 · Zhen Qu, Xian Tao, Xiaoyi Bao, Dingrong Wang 외 arxiv

Large multimodal models (LMMs) exhibit strong task generalization capabilities, offering new opportunities for zero-shot visual anomaly segmentation (ZSAS). However, existing LMM-based segmentation approaches still face …

How semantic and geometric information mutually reinforce each other in ToF object localization

2020-08-27 · Antoine Vanderschueren, Victor Joos, Christophe De Vleeschouwer

We propose a novel approach to localize a 3D object from the intensity and depth information images provided by a Time-of-Flight (ToF) sensor. Our method uses two CNNs. The first one uses raw depth and intensity images a…

Object Object Localization