Search papers, labs, and topics across Lattice.
This paper introduces an object-centered data acquisition method for 3D Gaussian Splatting (3DGS) using mobile phones, addressing the challenge of reliable mobile acquisition. The method employs on-device capture guidance, records onboard sensor signals, and aligns device orientations to a baseline frame for relative pose estimation. By mapping the camera's optical axis to an object-centered spherical grid and providing real-time area-weighted spherical coverage guidance, the method achieves superior reconstruction quality with fewer images compared to free capture and RealityScan.
Achieve higher quality 3D Gaussian Splatting reconstructions of objects from mobile phone captures using fewer images, thanks to a novel object-centered capture guidance system.
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.
