AI RESEARCH
EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation
arXiv CS.CV
•
ArXi:2512.00385v2 Announce Type: replace Superpoint-based pipelines provide an efficient alternative to point- or voxel-based 3D semantic segmentation, but are often bottlenecked by their CPU-bound partition step. We propose a learnable, fully GPU partitioning algorithm that generates geometrically and semantically coherent superpoints 13$\times$ faster than prior methods. Our module is compact (under 60k parameters), trains in under 20 minutes with a differentiable surrogate loss, and requires no handcrafted features.