Search Results for author: Mahdi Saleh

Found 9 papers, 5 papers with code

Rotation-Invariant Transformer for Point Cloud Matching

no code implementations14 Mar 2023 Hao Yu, Zheng Qin, Ji Hou, Mahdi Saleh, Dongsheng Li, Benjamin Busam, Slobodan Ilic

The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted descriptors, but it is despised by most of the recent deep matchers.

Data Augmentation

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

no code implementations27 Sep 2022 Hao Yu, Ji Hou, Zheng Qin, Mahdi Saleh, Ivan Shugurov, Kai Wang, Benjamin Busam, Slobodan Ilic

More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.

Point Cloud Registration

CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning

no code implementations31 Jul 2022 Mahdi Saleh, Yige Wang, Nassir Navab, Benjamin Busam, Federico Tombari

The proposed hierarchical model achieves state-of-the-art shape classification in mean accuracy and yields results on par with the previous segmentation methods while requiring significantly fewer computations.

Scene Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.