Stars
A D&D5e character sheet template for Obsidian semi-automated to feel like a healthy mix of a classic paper/pdf sheet and DnDBeyond/Roll20!
An open-source AI agent that brings the power of Gemini directly into your terminal.
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
OptiX SDK headers, everything needed to build & run OptiX applications. SDK samples not included.
Ray-tracing collision detection library
Parallel Transformation of Bounding Volume Hierarchies into Oriented Bounding Box Trees
Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset
cuCIM - RAPIDS GPU-accelerated image processing library
This is a repository for listing papers on scene graph generation and application.
gradslam is an open source differentiable dense SLAM library for PyTorch
Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia, Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)
This is a complete package of recent deep learning methods for 3D point clouds in pytorch (with pretrained models).
[CVPR 2024] Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
Numbast is a tool to build an automated pipeline that converts CUDA APIs into Numba bindings.
[ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"
Flexible Python configuration system. The last one you will ever need.
[RSS2024] Official implementation of "Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation"
A python wrapper of Fbow ( Fast Bag of Word) depends on Pybind11 only
pySLAM-D is a real-time SLAM algorithm for UAV aerial stitching. Includes additional features and refactored code inspired by BU's implementation https://github.com/armandok/pySLAM-D
[T-RO 2024] Uni-Fusion: Universal Continuous Mapping
Large World Model -- Modeling Text and Video with Millions Context
[ICRA 2024 Oral] Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"