raphaelsulzer/dsr-benchmark
[TPAMI 2024] A Survey and Benchmark for Automatic Surface Reconstruction from Point Clouds
This project helps researchers and engineers working with 3D data evaluate how well their algorithms reconstruct solid surfaces from raw scan data. It takes in point cloud data, which are like many individual dots representing a surface, and compares the 3D surface models your algorithm creates against known, accurate 3D models. This tool is designed for specialists developing or improving methods for 3D surface reconstruction.
Use this if you are developing a new algorithm to reconstruct 3D surfaces from point cloud scans and need standardized datasets and metrics to test its accuracy.
Not ideal if you are a practitioner looking for an out-of-the-box solution to reconstruct a single 3D surface, rather than evaluating a new reconstruction method.
Stars
40
Forks
5
Language
Python
License
MIT
Category
Last pushed
Dec 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/raphaelsulzer/dsr-benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
daavoo/pyntcloud
pyntcloud is a Python library for working with 3D point clouds.
yangyanli/PointCNN
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
torch-points3d/torch-points3d
Pytorch framework for doing deep learning on point clouds.
yogeshhk/MidcurveNN
Computation of Midcurve of Thin Polygons using Neural Networks
charlesq34/pointnet2
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space