A guide to Quantize Yolov8 Object Detection models using ONNX.

Godot Engine – Multi-platform 2D and 3D game engine

Godot Engine official documentation

An MIT rewrite of YOLOv9

Windows inside a Docker container.

High-resolution models for human tasks.

A lightweight library for portable low-level GPU computation using WebGPU.

[3DV'24 Best Paper Honorable Mention] NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM

Intel® NPU Acceleration Library

DUSt3R: Geometric 3D Vision Made Easy

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

A cross compile environment Docker image, can be used like docker multiarch image without speed penalty.

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

CUDA on non-NVIDIA GPUs

We write your reusable computer vision tools. 💜

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Character Animation (AnimateAnyone, Face Reenactment)

[RAL/IROS 2022] OverlapTransformer: An Efficient and Yaw-Angle-Invariant Transformer Network for LiDAR-Based Place Recognition.

BoT-SORT + YOLOX implemented using only onnxruntime, Numpy and scipy, without cython_bbox and PyTorch. Fast human tracker. OSNet is not used.

TensorRT Extension for Stable Diffusion Web UI

[CVPR 2024] Code release for "Unsupervised Universal Image Segmentation"

[ICCV'23] Cascade-DETR: Delving into High-Quality Universal Object Detection

An unofficial pytorch implementation of BakedSDF

Unofficial Implementation of Animate Anyone

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"