Research map / 3D vision / 3D generation
GeoGraph: Graph-based multi-view object detection with geometric cues end-to-end
Ahmed Samy Nassar, Stefano D’Aronco, Sébastien Lefèvre, Jan D. Wegner
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace SSD with EfficientDet detector | SSD-ReID-Geo · Pasadena Multi-View ReID | Detection mAP: 0.682 -> 0.742 | Improved |
| replace SSD with EfficientDet detector | SSD-ReID-Geo · Mapillary traffic signs | Detection mAP: 0.902 -> 0.919 | Improved |
| use GNN instead of siamese CNN (ablation) | Siamese CNN · Pasadena Multi-View ReID (GT crops) | F1-score: 0.509 -> 0.601 | Improved |
| use GNN instead of siamese CNN (ablation) | Siamese CNN · Mapillary traffic signs (GT crops) | F1-score: 0.721 -> 0.823 | Improved |
| add geometric camera cues (GNN-Geo) (ablation) | GNN · Pasadena Multi-View ReID (GT crops) | F1-score: 0.601 -> 0.640 | Improved |
| add geometric camera cues (GNN-Geo) (ablation) | GNN · Mapillary traffic signs (GT crops) | F1-score: 0.823 -> 0.873 | Improved |
| increase views from 2 to 4 (ablation) | GeoGraph · Pasadena Multi-View ReID | Geo-localization error (m): 2.94 -> 2.75 | Improved |
| increase views from 2 to 4 (ablation) | GeoGraph · Pasadena Multi-View ReID | Re-ID mAP: 0.754 -> 0.763 | Improved |
| increase views from 2 to 6 (ablation) | GeoGraph · Mapillary traffic signs | Re-ID mAP: 0.902 -> 0.924 | Improved |
| increase views from 2 to 6 (ablation) | GeoGraph · Mapillary traffic signs | Geo-localization error (m): 3.88 -> 4.21 | Hurt |
| fully connected dense edges including within-image nodes (ablation) | GNN graph construction · Pasadena Multi-View ReID and Mapillary traffic signs | Re-ID | Improved |
Closest papers by meaning
- Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph (ECCV 2022 · similarity 0.87)
- Learning Multi-View Camera Relocalization With Graph Neural Networks (CVPR 2020 · similarity 0.87)
- GPS-Net: Graph Property Sensing Network for Scene Graph Generation (CVPR 2020 · similarity 0.87)
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud (CVPR 2020 · similarity 0.86)
- Spatial-Aware Graph Relation Network for Large-Scale Object Detection (CVPR 2019 · similarity 0.86)
- A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective (TPAMI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
