Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

🩺 首个会看胸部X光片的中文多模态医学大模型 | The first Chinese Medical Multimodal Model that Chest Radiographs Summarization.

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.

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

Grounded Language-Image Pre-training

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

The implementation of the paper 'ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation' (CVPR2022)

Point-NeRF: Point-based Neural Radiance Fields

A procedural Blender pipeline for photorealistic training image generation

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

pyntcloud is a Python library for working with 3D point clouds.

Perception toolkit for sim2real training and validation in Unity

📖 A curated list of resources dedicated to synthetic data

Unreal Engine 4 C++ examples

[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains

A demo project for indoor pet detection using Unity generated synthetic data.

Real-time, open-source simulation of transparent objects for deep learning applications 牛啊牛啊

cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

A virtual environment that allows changing isolated features in the image 这个好像是UnrealCV的升级版

ICCV 2021 paper with code

Urban environment simulation in Unity3d. A model of sidewalk mobile robot is added with ROS integration. A synthetic data collection pipeline is available. Dynamic objects motion is provided with t…

CVPR 2021 论文和开源项目合集

Code base for physics-based photorealistic rendering within the scope of Bosch BCAI AMIRA probject

Python scripts for generating synthetic stereo depth data using the UnrealCV library.

Multimodal Fusion via Teacher-Student Network for Indoor Action Recognition

SynthDet - An end-to-end object detection pipeline using synthetic data

NVIDIA Dataset Utilities (NVDU)

Real-time multi-person tracker using YOLO v5 and deep sort