MaLCA: Point Cloud Registration with Mamba-Enhanced Features and Local Correspondence Augmentation

High-quality correspondences are critical to the accuracy and robustness of point cloud registration. Existing Transformer-based methods are fundamentally constrained by the quadratic computational complexity of self-attention, resulting in limited scalability. Moreover, conventional outlier removal...

Olles dieđut

Furkejuvvon:

Bibliográfalaš dieđut
Váldodahkkit:	Yuchen Huo, Longyun Zhang, Huijuan Guo, Jingyi Gong, Liqun Kuang, Xie Han, Fengguang Xiong
Materiálatiipa:	Artigo
Giella:	Inglês
Almmustuhtton:	MDPI AG 2026-05-01
Ráidu:	Algorithms
Fáttát:	point cloud registration state space model Mamba correspondence augmentation
Liŋkkat:	https://www.mdpi.com/1999-4893/19/5/380
Fáddágilkorat:	Lasit fáddágilkoriid Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!

MaLCA: Point Cloud Registration with Mamba-Enhanced Features and Local Correspondence Augmentation

Geahča maid