GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end
arXiv:2003.10151
Abstract
In this paper we propose an end-to-end learnable approach that detects static urban objects from multiple views, re-identifies instances, and finally assigns a geographic position per object. Our method relies on a Graph Neural Network (GNN) to, detect all objects and output their geographic positions given images and approximate camera poses as input. Our GNN simultaneously models relative pose and image evidence, and is further able to deal with an arbitrary number of input views. Our method is robust to occlusion, with similar appearance of neighboring objects, and severe changes in viewpoints by jointly reasoning about visual image appearance and relative pose. Experimental evaluation on two challenging, large-scale datasets and comparison with state-of-the-art methods show significant and systematic improvements both in accuracy and efficiency, with 2-6% gain in detection and re-ID average precision as well as 8x reduction of training time.
References in corpus (13)
- Semi-Supervised Classification with Graph Convolutional Networks
- Neural Message Passing for Quantum Chemistry
- Spectral Networks and Locally Connected Networks on Graphs
- Fast Graph Representation Learning with PyTorch Geometric
- DeepInf: Social Influence Prediction with Deep Learning
- Learning Deep Generative Models of Graphs
- Fake News Detection on Social Media using Geometric Deep Learning
- From Google Maps to a Fine-Grained Catalog of Street trees
- Automatic Discovery and Geotagging of Objects from Street View Imagery
- Edge Contraction Pooling for Graph Neural Networks
- Towards seamless multi-view scene analysis from satellite to street-level
- Simultaneous multi-view instance detection with learned geometric soft-constraints
- Automated Detecting and Placing Road Objects from Street-level Images