3DGS-to-PC: 3D Gaussian Splatting to Dense Point Clouds [3D-VAST: ICCVW 2025]
Image Signal Processing (ISP) Guide. Learn all about the process of converting an image/video into digital form by performing tasks like noise reduction, filtering, auto exposure, autofocus, HDR correction, and image sharpening with a Specialized type of media processor.
Morphing and Sampling Network for Dense Point Cloud Completion (AAAI2020)
Implementations of a rather simple version of the Iterative Closest Point algorithm in various languages.
Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions (RAL 2022)
Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296
[ICCV 2021] Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
An SDK for multi-agent collaborative perception.
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"
[CVPR2023] Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration
PVT: Point-Voxel Transformer for 3D Deep Learning
Numpy-only dynamic object removal for LiDAR point clouds — 3D box crop + temporal filtering. No GPU, no deep learning.
Introduction to Point Cloud Processing
Official GitHub repo for VecKM. A very efficient and descriptive local geometry encoder / point tokenizer / patch embedder. ICML2024.
This code is designed to extract a representative curve (or a thin center line) from a noisy 3D point cloud, especially when the point cloud has discernible geometric patterns. Given a noisy point cloud that has an inherent structure or shape, the goal is to identify and trace a continuous curve that best captures the essence of that shape.
[CVPR 2025] SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
FLS point cloud registration (ISRR 2022)
diffCheck is a CAD-integrated tool for evaluating digital timber fabrication processes.
[AAAI 2023 Distinguished Paper] Two Heads are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation
Benchmarking KISS-ICP, DLIO, FAST-LIO2 and GLIM on Livox Mid360 datasets using ROS2 Humble and EVO trajectory evaluation against ground-truth data.
To associate your repository with the point-cloud-processing topic, visit your repo's landing page and select "manage topics."