Implementation of "Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation" from CVPR Workshop on Human Motion Generation 2024.

A TTS that fits in your CPU (and pocket)

A Python library for reading and writing PDF, powered by QPDF

21 Lessons, Get Started Building with Generative AI

DeepStream IPC (Inter-Process Communication)

RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Reference PyTorch implementation and models for DINOv3

ViPE: Video Pose Engine for Geometric 3D Perception

Highly accurate and efficient VSLAM system for Python

About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]

SoTA open-source TTS

Universal Vision Workloads

[ICRA 2025] ELite: Ephemerality meets LiDAR-based Lifelong Mapping

[NeurIPS 2024] MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning

Build computer vision models in a fraction of the time and with less data.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Sensor Fusion ROS2 Package enabling dynamic simplified tuning of an Extended Kalman Filter

[ICCV 2025] PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

We write your reusable computer vision tools. 💜

[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Python wrapper to small NORB dataset

(CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting

A minimal yet unstoppable blueprint for multi-agent AI—anchored by the rare, far-reaching “Multi-Agent AI DAO” (2017 Prior Art)—empowering a new wave of superintelligent on-chain Agents.