CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

[ICRA2023] Implementation of Visual Language Maps for Robot Navigation

Code for sim-to-real transfer of a pretrained Vision-and-Language Navigation (VLN) agent to a robot using ROS.

An open-source platform for Visual AI.

A collection of 3D reconstruction papers in the deep learning era.

Segment Anything in 3D with NeRFs (NeurIPS 2023)

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

tutorial for writing custom pytorch cpp+cuda kernel, applied on volume rendering (NeRF)

Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

A unified framework for 3D content generation.

A General NeRF Acceleration Toolbox in PyTorch.

Hosts the Multiface dataset, which is a multi-view dataset of multiple identities performing a sequence of facial expressions.

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 PyTorch Implementation of paper "Vision Transformer for NeRF-Based View Synthesis from a Single Input Image", WACV 2023.

ROS python API tutorials code cross-compilation

RTAB-Map's ROS package.

RTAB-Map library and standalone application

针对带有RGBD相机的服务机器人，物流机器人等。具有：语义地图构建、定位导航、三维重构、重定位、动态物体识别、移动避障、手势识别、人脸识别、语音合成与识别等功能

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Visual Inertial Odometry with SLAM capabilities and 3D Mesh generation.

ROS wrapper for Kimera-VIO

Real-Time 3D Semantic Reconstruction from 2D data

CubeSLAM: Monocular 3D Object Detection and SLAM

Cube SLAM 个人注释版

Python package for the evaluation of odometry and SLAM