Object centric angle refinement improves irregular turntable 3D reconstruction
OC-GS: Gaussian Splatting for Irregular Turntable Capture
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Making 3D models of objects using turntables relies on evenly spaced photos, but uneven spinning and missed images cause problems. The authors developed a method called OC-GS that adjusts each photo’s angle while keeping the camera and rotation settings consistent. This approach helps make better 3D models from fewer and irregular pictures. Testing showed that refining the angles this way gives clearer object images than methods that don’t adjust angles.
What this means in practice
- •For 3d scanning technicians: Generate clearer 3D models from irregularly spaced and missed photos in turntable-based scans by refining image angles consistently with shared rotation parameters.
- •For augmented reality developers: Improve real-time object reconstruction quality from sparse camera inputs by updating camera angles within a consistent motion framework.
Authors
Jae Joong Lee, Bedrich Benes
Abstract
Uneven rotation and dropped frames make equal-angle assumptions unreliable for turntable reconstruction. We present OC-GS, an object-centric Gaussian splatting that refines each image's angle while maintaining a shared camera, rotation axis, and pivot. This orbit-consistent refinement jointly optimizes image-derived geometry and angles to reconstruct objects from sparse, irregular captures. On rendered objects with 12, 8, and 6 irregularly spaced views, OC-GS achieves mean foreground PSNR scores of 21.26, 19.36, and 15.83dB, respectively, exceeding all four evaluated pose-free Gaussian splatting baselines in each condition. Under a shared trainer, refining image-estimated angles improves mean foreground PSNR by 7.88dB over keeping those estimates fixed. An ablation study shows that both image-derived angle initialization and the shared motion model contribute to the improvement. On real captures, OC-GS's refinement increases mean foreground PSNR by 0.70dB. Results show that refining uncertain angles within a shared motion model improves reconstruction from sparse, irregular turntable captures.