⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

The jetson-examples repository by Seeed Studio offers a seamless, one-line command deployment to run vision AI and Generative AI models on the NVIDIA Jetson platform.

[ICCV 2023] DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Code for the "Learning to Estimate Two Dense Depths from LiDAR and Event Data" article

国内首个占据栅格网络全栈课程《从BEV到Occupancy Network，算法原理与工程实践》，包含端侧部署。Surrounding Semantic Occupancy Perception Course for Autonomous Driving (docs, ppt and source code) 在线课程主页：http://111.229.117.200:8100/ (作者独立搭建)

Enjoy the magic of Diffusion models!

Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models

Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion (ICRA2024)

ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English versi…

[NeurIPS 2023 Track Datasets and Benchmarks] OpenLane-V2: The First Perception and Reasoning Benchmark for Road Driving

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

Course projects for the Sensor Fusion Nanodegree program on Udacity.

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

Is it a perfect portrait!

Source code for Dain-App

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Official code for ICCV2021 paper "M3D-VTON: A Monocular-to-3D Virtual Try-on Network"

End-to-end, automatic face swapping pipeline

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

A new play-and-plug method of controlling an existing generative model with conditioning attributes and their compositions.

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

A unified 3D Transformer Pipeline for visual synthesis

Official code for NeurIPS 2021 paper "Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN"