Stars
Segmentator for clustering on meshes or pointclouds
Code for "SAM-guided Graph Cut for 3D Instance Segmentation" ECCV 2024
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Make your wildest 3D ConvNet dream architectures come true
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
This is an open-source repository for semantic based point cloud tasks, and we aim to provide a comprehensive summary of various semantic based point cloud tasks.
A no dependency, header-only, fast supervoxel segmentation library for 3D point clouds
This Python program is used for fitting data points to an 2D ellipse. Several different approaches are used and compared to each other. It is programmed in Python 3.7.9. (windows version). The para…
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
Augmentation package for 3d data based on albumentaitons
A resource repository for 3D machine learning
MINSU3D: MinkowskiEngine-powered Scene Understanding in 3D
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
Industrial Language-Image Dataset (ILID), a web-crawled dataset containing language-image samples from various web catalogs, representing parts/components from the industrial domain.
Code for "Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers" (NeurIPS 2024)
Zotero plugin for fetching number of citations from Google Scholar.
Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Insert and import citations, bibliographies, notes, and PDF annotations from Zotero into Obsidian.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Code for training and evaluation on the "Industrial Language-Image Dataset (ILID)".