Search Results for author:
Found 2 papers, 0 papers with code
D3Former: Jointly Learning Repeatable Dense Detectors and Feature-enhanced Descriptors via Saliency-guided Transformer
Notably, tests on 3DLoMatch, even with a low overlap ratio, show that our method consistently outperforms recently published approaches such as RoReg and RoITr.
Bundle Optimization for Multi-aspect Embedding
Understanding semantic similarity among images is the core of a wide range of computer vision applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
