语义引导的3D高斯点云对瞬态物体去除
Semantic-Guided 3D Gaussian Splatting for Transient Object Removal
AI总结：
本文提出基于语义分类的3D高斯点云瞬态去除方法，通过CLIP相似度分数和阈值校准提升重建质量，减少内存开销并保持实时渲染性能。
摘要：
在非正式多视角捕获中，瞬态物体会导致3D高斯点云（3DGS）重建出现鬼影伪影。现有解决方案依赖于显著的内存消耗的场景分解或基于运动的启发式方法，这些方法容易受到视差歧义的影响。本文提出了一种语义过滤框架，利用视觉-语言模型进行类别感知的瞬态去除。在训练迭代中，渲染视角与干扰文本提示之间的CLIP相似度分数被累积到每个高斯点上。超过校准阈值的高斯点会经历不透明度正则化和周期性修剪。与基于运动的方法不同，语义分类通过独立于运动模式识别物体类别来解决视差歧义。在RobustNeRF基准测试中，实验表明在四个序列中，与 vanilla 3DGS 相比，重建质量有持续提升，同时保持了最小的内存开销和实时渲染性能。阈值校准和与基线的比较验证了语义引导作为在具有可预测干扰类别场景中瞬态去除的实用策略。
英文摘要：
Transient objects in casual multi-view captures cause ghosting artifacts in 3D Gaussian Splatting (3DGS) reconstruction. Existing solutions relied on scene decomposition at significant memory cost or on motion-based heuristics that were vulnerable to parallax ambiguity. A semantic filtering framework was proposed for category-aware transient removal using vision-language models. CLIP similarity scores between rendered views and distractor text prompts were accumulated per-Gaussian across training iterations. Gaussians exceeding a calibrated threshold underwent opacity regularization and periodic pruning. Unlike motion-based approaches, semantic classification resolved parallax ambiguity by identifying object categories independently of motion patterns. Experiments on the RobustNeRF benchmark demonstrated consistent improvement in reconstruction quality over vanilla 3DGS across four sequences, while maintaining minimal memory overhead and real-time rendering performance. Threshold calibration and comparisons with baselines validated semantic guidance as a practical strategy for transient removal in scenarios with predictable distractor categories.
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。
