jianboqi/CSF

LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation

What it solves

CSF is designed to filter airborne LiDAR data to separate ground points from non-ground points (such as vegetation or buildings) in a point cloud.

How it works

It uses a cloth simulation filter (CSF) method, which which simulates a cloth draped over the point cloud from the bottom up to identify ground surfaces.

Who it’s for

Professionals and researchers working with LiDAR data, point cloud processing, and remote sensing, with support for Python, Matlab, R, and C++.

Highlights

  • Multi-language support: Provides interfaces for Python (via pip), Matlab, R, and C++.
  • Integration: Works seamlessly with common LiDAR tools like Laspy and CloudCompare.
  • Extensible: Built with CMake for easy integration as a static library in C++ projects.
  • Flexible data import: Supports reading data from .las files (via Laspy) and plain text files.

Related

  • Project
    cvg/DeepLSD

    DeepLSD is a high-precision line segment detector that combines deep learning with image gradients to extract and refine line segments from real-world images.

  • Project
    huawei-bayerlab/marigold-v2

    Marigold V2 is a research codebase that repurposes a pretrained diffusion transformer (Qwen‑Image‑Edit‑2509) into fast, single‑step predictors for monocular depth, see‑through depth, surface normals, and albedo. It offers cheap fine‑tuning (≈5 days on a single 32 GB GPU), state‑of‑the‑art benchmark results, ready‑to‑use inference/evaluation scripts, and a modular YAML‑driven training framework that can be extended to new dense‑vision tasks.

  • Project
    chenwei-zhao/captcha-recognizer

    A deep learning-based library for identifying the gap coordinates and confidence levels in slider CAPTCHAs.

  • Project
    LibreYOLO/libreyolo

    An MIT-licensed computer vision library that provides a single API for detection, segmentation, pose, depth, OCR, and other vision tasks, including training and export tools.