galmetzer/self-sample
Single shape Deep Point Cloud Consolidation [TOG 2021]
This project helps 3D graphics professionals and researchers clean up 'noisy' or incomplete 3D point cloud data. You provide a single 3D point cloud, and it outputs a consolidated, smoother version of that same shape. This is ideal for anyone working with scanned 3D models or generated point clouds that need refinement.
No commits in the last 6 months.
Use this if you have a single 3D point cloud model that needs to be denoised, consolidated, or made more complete.
Not ideal if you need to process multiple 3D point clouds of different shapes or require complex mesh generation directly from the point cloud.
Stars
46
Forks
8
Language
Python
License
MIT
Category
Last pushed
May 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/galmetzer/self-sample"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
drprojects/superpoint_transformer
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds