Stars
DarkGPT is an OSINT assistant based on GPT-4-200K (recommended use) designed to perform queries on leaked databases, thus providing an artificial intelligence assistant that can be useful in your t…
A curated list of awesome commands, files, and workflows for Claude Code
Official implementation of "Emergent Temporal Correspondences from Video Diffusion Models"
Impacket is a collection of Python classes for working with network protocols.
Self-Supervised Speech Pre-training and Representation Learning Toolkit
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
PyTorch code and models for VJEPA2 self-supervised learning from video.
High-resolution models for human tasks.
[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"
A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT
[ICIP2024] Real-time Monocular Depth Estimation on Embedded Systems
Metric depth estimation from a single image
【CVPR 2025 Highlight】MonSter: Marry Monodepth to Stereo Unleashes Power
[CVPR25] Official repository for the paper: "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"
About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
Create and control 3D shapes using hand gestures in real-time. Built with mediapipe computer vision and threejs
Real-time webcam demo with SmolVLM and llama.cpp server
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin9…
TripoSR: Fast 3D Object Reconstruction from a Single Image
[CVPRW2025] Studying Image Diffusion Features for Zero-Shot Video Object Segmentation