CubifyGS: 面向对象的3D高斯泼溅用于终身动态场景维护
CubifyGS: Object-Centric 3D Gaussian Splatting for Lifelong Dynamic Scene Maintenance
AI总结:
提出CubifyGS,一种面向对象的映射框架,通过将可移动实例建模为可重用高斯资产,并采用事件触发自适应优化,实现刚性物体重排下的高效动态场景维护。
摘要:
在刚性物体重排下的终身场景映射仍然是机器人学中的一个基本挑战。虽然3D高斯泼溅(3DGS)能够实现高保真建模,但原始级别的更新常常导致持续的鬼影和缓慢的恢复。我们提出CubifyGS,一种面向对象的映射框架,将动态维护从被动重新优化转变为主动资产管理。CubifyGS将可移动实例建模为可重用的高斯资产,检测物体的出现和消失,并通过资产检索、刚性变换和显式剪枝而非从头重建来更新地图。为了解决这些编辑后的几何空洞和局部光度不匹配,我们进一步提出了一种事件触发的自适应优化策略,将计算集中在受影响的区域。我们在新构建的高保真动态基准上验证了我们的方法,结果表明,在评估的物体重排设置中,CubifyGS在伪影抑制和维护效率方面优于代表性的可复现基线。
英文摘要:
Lifelong scene mapping under rigid object rearrangement remains a fundamental challenge in robotics. While 3D Gaussian Splatting (3DGS) enables high-fidelity modeling, primitive-level updates often cause persistent ghosting and slow recovery. We propose CubifyGS, an object-level mapping framework that shifts dynamic maintenance from passive re-optimization to active asset management. CubifyGS models movable instances as reusable Gaussian assets, detects object appearance and disappearance, and updates maps through asset retrieval, rigid transformation, and explicit pruning rather than reconstruction from scratch. To address geometric voids and local photometric mismatch after such edits, we further propose an event-triggered adaptive optimization strategy that focuses computation on affected regions. We validate our approach on a newly constructed high-fidelity dynamic benchmark, demonstrating that CubifyGS improves artifact suppression and maintenance efficiency over representative reproducible baselines in the evaluated object-rearrangement setting.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。