Abstract The field of 3D reconstruction from multi‐view images has advanced rapidly thanks to 3D Gaussian Splatting (3DGS), which enables efficient and photorealistic scene representation. However, optimizing 3DGS requires high‐quality images from various viewpoints with accurate camera poses. The repeated collection of such data demands significant human effort, which poses a major constraint in practical applications. To address this issue, automated capturing systems that uses a turntable and fixed camera are widely employed. In a turntable setup, the background remains stationary while the object rotates. Therefore, preprocessing to remove the backgrond is essential, but the preprocessing reduces the number of reliable feature matches, which destabilizes Structure‐from‐Motion (SfM). This results in inaccurate camera poses, which degrades the quality of 3DGS reconstruction. We propose a novel method to optimize 3DGS in a turntable setup without SfM by leveraging the prior knowledge that objects rotate around a central axis. Unlike previous SfM‐free methods that estimate camera poses for each frame, our approach reduces the complexity of optimization by representing rotations with a single global rotation axis. The estimated rotation is directly applied to the 3D Gaussians, producing motion defined as rotation flow. This rotation flow is then aligned with optical flow to provide strong geometric supervision. Through uncertainty‐to‐detail flow scheduling, our approach remains stable during the initial training stage when the geometry of the Gaussian set is still inaccurate. On the NeRF‐Synthetic dataset and on real‐world datasets captured with a turntable, our method outperforms existing SfM‐free approaches in both reconstruction quality and training speed, and even demonstrates performance comparable to 3DGS optimized with precise camera poses.

Recently, 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for reconstructing high-quality, photorealistic 3D representations of real-world scenes. However, editing 3DGS remains more challenging than mesh-based approaches as it lacks explicit geometry and requires view-consistent updates across Gaussians. Previous approaches have relied primarily on text-driven generative models for 3D Gaussian editing, limiting direct control over specific visual appearances. In this study, we propose a texture editing framework for 3DGS that leverages only a single user-modified image. Our approach maintains coherence across multiple views while accounting for the corresponding lighting adjustments in the edited region. We introduce three key techniques to achieve this: (1) aligned edit propagation, which transfers local edits from the reference view to other viewpoints; (2) mask-based filtering, which restricts modifications to relevant Gaussians and prevents unintended changes; and (3) opacity-based selection, which identifies Gaussians with the most significant visual impact on the edited texture. Through both qualitative and quantitative evaluations on synthetic and real-world datasets, we demonstrate that our method achieves more precise and spatially controllable 3DGS editing than existing techniques. We expect these techniques to pave the way for more intuitive 3D Gaussian Splatting editing pipelines and inspire future research.