Street_gaussians

Visit Tool

Street Gaussians is an open-source computer vision tool that models dynamic urban scenes. It uses Gaussian Splatting for realistic 3D reconstructions from video data.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is street_gaussians?

Street Gaussians is an open-source project presented at ECCV 2024, focusing on modeling dynamic urban scenes using Gaussian Splatting. This tool provides a framework for researchers and developers to reconstruct complex, moving urban environments from video data. It includes functionalities for data preparation, such as converting Waymo Open Dataset, generating LiDAR depth, and creating sky masks. Users can configure parameters based on 3D Gaussian Splatting, train models, render scenes, and visualize results. The project offers scripts for training and rendering on example and experimental Waymo scenes, making it a valuable resource for advancing research in dynamic 3D scene reconstruction.

Best used for

Ideal for computer vision researchers and developers who need to model dynamic urban scenes, reconstruct complex 3D environments from video, and experiment with Gaussian Splatting techniques. Especially valuable for academic research and development in autonomous driving and urban planning simulations.

Common actions

model dynamic scenes

reconstruct 3D environments

implement Gaussian Splatting

process urban datasets

face swapping"AI Agents"github copilotautomated workflowopen-sourcecollaborationlow-code/no-codeworkflowsdeepfake

Capabilities

Key features

Dynamic urban scene modeling
Gaussian Splatting implementation
Waymo Open Dataset integration
LiDAR depth generation
Sky mask generation
Configurable training parameters
3D scene rendering

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What kind of data does Street Gaussians use for modeling?

Street Gaussians primarily uses the Waymo Open Dataset for modeling dynamic urban scenes. It includes scripts for converting and preprocessing this dataset, generating LiDAR depth information, and creating sky masks to enhance the reconstruction process.

Can I use Street Gaussians with my own custom dataset?

The project currently provides detailed instructions for preparing the Waymo Open Dataset. While there is a placeholder for 'Prepare Custom Dataset. TODO', it indicates that support for custom datasets is planned but not yet fully implemented or documented.

What are the system requirements for running Street Gaussians?

To run Street Gaussians, you need a Python 3.8 environment with specific PyTorch versions (e.g., 1.13.1+cu116) corresponding to your CUDA version. It also requires installing several submodules like diff-gaussian-rasterization and simple-knn, indicating a need for GPU acceleration.

Trending

Subcategories trending in Content & Design

Image Generation AI Writing Assistants Audio & Music Video Generation Photo Editing Graphic Design

Trending

Also listed in

This tool also appears in

Research & Education › Academic Research Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce