An Object-Centered Data Acquisition Method for 3D Gaussian Splatting using Mobile Phones

TL;DR

This paper introduces a mobile phone-based data acquisition method for 3D Gaussian Splatting that guides users for better, more uniform object-centered 3D reconstructions with fewer images.

Contribution

It provides an on-device capture guidance system and real-time spherical coverage computation to improve 3D data acquisition quality for Gaussian Splatting.

Findings

Achieves superior reconstruction quality with fewer images than existing methods.

Provides more comprehensive and uniform viewpoint coverage during acquisition.

Outperforms RealityScan and free-capture strategies in experiments.

Abstract

Data acquisition through mobile phones remains a challenge for 3D Gaussian Splatting (3DGS). In this work we target the object-centered scenario and enable reliable mobile acquisition by providing on-device capture guidance and recording onboard sensor signals for offline reconstruction. After the calibration step, the device orientations are aligned to a baseline frame to obtain relative poses, and the optical axis of the camera is mapped to an object-centered spherical grid for uniform viewpoint indexing. To curb polar sampling bias, we compute area-weighted spherical coverage in real-time and guide the user's motion accordingly. We compare the proposed method with RealityScan and the free-capture strategy. Our method achieves superior reconstruction quality using fewer input images compared to free capture and RealityScan. Further analysis shows that the proposed method is able to obtain more comprehensive and uniform viewpoint coverage during object-centered acquisition.