MaRO-GS：来自不一致多视图掩码的掩码鲁棒对象中心高斯泼溅
MaRO-GS: Mask-Robust Object-Centric Gaussian Splatting from Inconsistent Multi-view Masks
浏览论文内容
中文总结 AI 辅助
提出MaRO-GS，一种直接优化目标对象高斯且对不一致掩码鲁棒的3DGS框架，通过视图过滤、密度控制和剪影对齐损失，提升重建精度与效率，PSNR最大增益2.05 dB。
中文摘要 AI 辅助
我们解决了在高斯泼溅中从多视图图像进行精确3D对象重建的挑战。现有的对象级3DGS方法重建整个场景，而不是直接优化目标对象，即使只需要目标对象时也是如此，这带来了大量的计算开销。它们还依赖2D分割掩码将高斯与对象关联，但这些掩码在不同视图之间往往不一致。这种不一致性破坏了高斯优化，并产生错误监督的高斯，降低了对象重建的保真度。为了克服这些限制，我们提出了MaRO-GS，一个3DGS框架，直接从对象掩码的多视图图像中优化目标对象高斯，并且对不一致的监督保持鲁棒。为了可靠的监督，掩码可靠性视图过滤排除了不可靠的视图。对象支持的高斯密度控制抑制了与目标对象无关的高斯，并防止背景致密化，而剪影对齐的对象损失保持了对象聚焦的优化。跨多个数据集的广泛实验表明，MaRO-GS提高了PSNR、分割精度和计算效率，在小对象LERF-Mask数据集上取得了最大的PSNR增益2.05 dB。
英文摘要
We address the challenge of accurate 3D object reconstruction from multi-view images in Gaussian Splatting. Existing object-level 3DGS methods reconstruct the entire scene rather than directly optimizing the target object, even when only the target object is needed, which incurs substantial computational overhead. They also rely on 2D segmentation masks to associate Gaussians with objects, but these masks are often inconsistent across views. Such inconsistencies corrupt Gaussian optimization and produce incorrectly supervised Gaussians that degrade object reconstruction fidelity. To overcome these limitations, we propose MaRO-GS, a 3DGS framework that directly optimizes target-object Gaussians from object-masked multi-view images and remains robust to inconsistent supervision. For reliable supervision, mask-reliability view filtering excludes unreliable views. Object-supported Gaussian density control suppresses Gaussians irrelevant to the target object and prevents background densification, while Silhouette-aligned Object Loss maintains object-focused optimization. Extensive experiments across diverse datasets demonstrate that MaRO-GS improves PSNR, segmentation accuracy, and computational efficiency, with the largest PSNR gain of 2.05 dB on the small-object LERF-Mask dataset.
发表机构
- School of Computer Science and Engineering Kyungpook National University（庆北国立大学计算机科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。
