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

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)

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

Stable Diffusion web UI

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

A series of large language models developed by Baichuan Intelligent Technology

LAVIS - A One-stop Library for Language-Vision Intelligence

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

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

目标：构建一个更符合语言学的 llama 中英文分词器

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

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.

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

Template repository for creating and registering new methods in NerfStudio.

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Grounded Segment Anything: From Objects to Parts

Official Repository for CVPR 2023 paper PointAvatar: Deformable Point-based Head Avatars from Videos.

PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images

SMPLpix: Neural Avatars from 3D Human Models