Stars
A small-footprint noVNC (web-based) desktop Docker image
ROS packages for multi robot exploration, with custom set of parameters for efficient exploration in large environments
Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.
An open source approach to locally record and enable searching everything you view on your Mac.
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch
[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Memento is a Python app that records everything you do on your computer and lets you go back in time, search, and chat with a LLM (Large Language Model) to find back information about what you did.
CUDA accelerated rasterization of gaussian splatting
Open-source digital stylus using camera tracking and inertial measurements
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) fo…
Image-to-Image Translation in PyTorch
An overview of different quaternion implementations and their chosen order: x-y-z-w or w-x-y-z?
Here you'll find a growing collection of 3D models, textures, and images from inside NASA.
Simple, online, and realtime tracking of multiple objects in a video sequence.
2 Python API functions for point cloud conversion between Open3D and ROS. Compatible for XYZ and XYZRGB point type.
Point cloud registration of two intel D435i 3D cameras using the Iterative-Closest-Point algorithm.
A hierarchical multi-stage manipulation planner
Efficient bindings between Numpy and Eigen using Boost.Python
Dynamical movement primitives (DMPs), probabilistic movement primitives (ProMPs), and spatially coupled bimanual DMPs for imitation learning.