Awesome LLMs on Device: A Comprehensive Survey

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians

Ongoing research training gaussian splatting at scale by distributed system

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

一个基于 electron 的音乐软件

🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Labeling tool with SAM(segment anything model),supports SAM, SAM2, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

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

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

[ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

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

This is the pytorch implement of our paper "RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model"

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!

ncnn is a high-performance neural network inference framework optimized for the mobile platform

R2LIVE: A Robust, Real-time, LiDAR-Inertial-Visual tightly-coupled state Estimator and mapping package

Code for GAN2Shape (ICLR2021 oral)

Implementation of popular deep learning networks with TensorRT network definition API

Pytorch implementation of various Knowledge Distillation (KD) methods.

An awesome face technology repository.

VideoCapture封装，读取rtsp的实时帧

MOT using deepsort and yolov3 with pytorch