An Object-Centered Data Acquisition Method for 3D Gaussian Splatting using Mobile Phones
career value
224K/year
🤖 AI Summary
This work addresses the challenge of non-uniform viewpoint distribution and poor reconstruction quality when capturing object-centric data on mobile devices. To enable high-quality 3D Gaussian splatting, the authors propose a method that fuses IMU and camera data from mobile sensors to map calibrated camera optical axes onto a spherical grid, thereby constructing a uniform viewpoint index. An area-weighted spherical coverage metric is computed in real time to guide user motion during capture. This approach effectively mitigates polar sampling bias and significantly improves viewpoint uniformity. Experimental results demonstrate that, compared to RealityScan and unguided free-form capture strategies, the proposed method achieves superior reconstruction quality and more comprehensive viewpoint coverage using fewer input images.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
3D Gaussian Splatting
mobile data acquisition
object-centered capture
viewpoint coverage
spherical sampling bias
Innovation
Methods, ideas, or system contributions that make the work stand out.
3D Gaussian Splatting
object-centered acquisition
mobile phone capture
spherical coverage guidance
sensor-assisted reconstruction
🔎 Similar Papers
No similar papers found.
