# EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation

Source: [EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation](<https://www.sota2.com/research/paper/692e729cd6b0dd3342932329>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T05:00:11.826Z

Authors: Louis Geist, Loic Landrieu, Damien Robert

Published: 2025-11-29T08:21:51.000Z

## Abstract

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. Combine with a lightweight superpoint classifier, the full pipeline fits in $\<$2 MB of VRAM, scales to multi-million-point scenes, and supports real-time inference. With 72$\\times$ faster inference and 120$\\times$ fewer parameters, EZ-SP matches the accuracy of point-based SOTA models across three domains: indoor scans (S3DIS), autonomous driving (KITTI-360), and aerial LiDAR (DALES). Code and pretrained models are accessible at github.com/drprojects/superpoint\_transformer.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.00385>)

[PDF](<https://arxiv.org/pdf/2512.00385.pdf>)