IMCPT-SparseGM dataset is a new visual graph matching benchmark addressing partial matching and graphs with larger sizes, based on the novel stereo benchmark Image Matching Challenge PhotoTourism (IMC-PT) 2020. This dataset is released in CVPR 2023 paper Deep Learning of Partial Graph Matching via Differentiable Top-K.
| # images | # classes | avg # nodes | avg # edges | # universe | partial rate |
|---|---|---|---|---|---|
| 25765 | 16 | 21.36 | 54.71 | 50 | 57.3% |
Variants: IMCPT-SparseGM-50
This dataset is used in 1 benchmark:
No recent benchmark submissions available for this dataset.
No papers with results on this dataset found.