Awesome
<p align="center"> <!-- project badges --> <a href="https://research.zenseact.com/publications/splatad/"><img src="https://img.shields.io/badge/Project-Page-ffa"/></a> <!-- paper badges --> <a href="https://arxiv.org/abs/2411.16816"> <img src='https://img.shields.io/badge/arXiv-Page-aff'> </a> </p> <div align="center"> <h3 style="font-size:2.0em;">SplatAD</h3> <h4 style="font-size:1.5em;"> Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving </h4> </div> <div align="center"> <div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/_static/imgs/frontfig-stacked.jpg" /> <img alt="tyro logo" src="docs/_static/imgs/frontfig-stacked.jpg" width="80%"/> </picture> </div>Key Features · Planned Features · Project page
</div>About
<h4>Code to be released.</h4>This is the official repository for SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving. The code in this repository builds upon the open-source library gsplat, with modifications and extensions designed for autonomous driving data.
Key Features
- Efficient lidar rendering
- Projection to spherical coordinates
- Depth and feature rasterization for a non-linear grid of points
- Rolling shutter compensation for camera and lidar
Planned Features/TODOs
- [] Release code