A Fast Volumetric Capture and Reconstruction Pipeline for Dynamic Point Clouds and Gaussian Splats

TL;DR

This paper introduces a rapid, versatile volumetric capture and reconstruction system capable of producing high-quality 3D point clouds and Gaussian splats from RGB-D or RGB data, suitable for real-time deployment in uncontrolled environments.

Contribution

It enhances Gaussian splat reconstruction with a new regressor, supports flexible camera setups, and offers an open-source, easy-to-deploy framework for real-time 3D capture and visualization.

Findings

Supports in-the-wild operation with minimal setup

Achieves 5-10 FPS live preview

Provides high-quality reconstructions with optimized Gaussian splats

Abstract

We present a fast and efficient volumetric capture and reconstruction system that processes either RGB-D or RGB-only input to generate 3D representations in the form of point clouds and Gaussian splats. For Gaussian splat reconstructions, we took the GPS-Gaussian regressor and improved it, enabling high-quality reconstructions with minimal overhead. The system is designed for easy setup and deployment, supporting in-the-wild operation under uncontrolled illumination and arbitrary backgrounds, as well as flexible camera configurations, including sparse setups, arbitrary camera numbers and baselines. Captured data can be exported in standard formats such as PLY, MPEG V-PCC, and SPLAT, and visualized through a web-based viewer or Unity/Unreal plugins. A live on-location preview of both input and reconstruction is available at 5-10 FPS. We present qualitative findings focused on deployability and targeted ablations. The complete framework is open-source, facilitating reproducibility and further research.