OC-GS: Gaussian Splatting for Irregular Turntable Capture

2026-09-25

AI Summary

This study addresses the challenge of reconstructing objects from sparse, irregular views captured by turntables, where non-uniform rotation and frame drops invalidate equal-angle assumptions. To overcome this, we propose an object-centric Gaussian Splatting framework that jointly optimizes geometry and viewpoints under shared camera, rotation axis, and pivot constraints. Central to our approach is an orbit consistency refinement mechanism that integrates angle initialization with a shared motion model, transcending the limitations of conventional fixed-angle or independent pose optimization. Experimental results demonstrate that our method consistently outperforms baselines in PSNR across 12, 8, and 6 irregular views. Notably, angle refinement yields substantial PSNR improvements of 7.88 dB and 0.70 dB on synthetic and real-world scenes, respectively, significantly enhancing reconstruction quality under sparse and irregular viewing conditions.

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.

Problem

• turntable reconstruction
• irregular capture
• Gaussian Splatting
• sparse views
• pose refinement

Innovation

• Gaussian Splatting
• Turntable Reconstruction
• Orbit-Consistent Refinement
• Shared Motion Model
• Pose-Free