A generative speech model for daily dialogue.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Democratization of RT-2 "RT-2: New model translates vision and language into action"

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Multi-Camera Unified Pre-training via 3D Scene Reconstruction for DETR3D, BEVFormer, BEVDet, BEVDepth and Semantic Occupancy Prediction

误差状态卡尔曼ESKF滤波器融合GPS和IMU，实现更高精度的定位

A full Python implementation for real car surround view system

An academic alternative to Tesla's occupancy network for autonomous driving.

Visual odometry package based on hardware-accelerated NVIDIA Elbrus library with world class quality and performance.

A latent text-to-image diffusion model

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

The Reliable USB Formatting Utility

CVPR 2022 papers with code (论文及代码）

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

OpenMMLab Detection Toolbox and Benchmark