Visual Place Recognition
98 papers with code • 27 benchmarks • 19 datasets
Visual Place Recognition is the task of matching a view of a place with a different view of the same place taken at a different time.
In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).
This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.
We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph.
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
This is largely due to the difficulty in extracting local feature descriptors from a point cloud that can subsequently be encoded into a global descriptor for the retrieval task.
In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization.
Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world.
Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features.
The paper presents an approach to indoor personal localization on a mobile device based on visual place recognition.