用语义信息自动清除3D重建中的临时物体，效果好且不占内存。
Semantic-Guided 3D Gaussian Splatting for Transient Object Removal
- 通过视觉语言模型判断每个高斯点是否为干扰物
- 在四个数据集上显著减少鬼影，且保持实时渲染
- 适合有固定干扰物类别的场景，如行人、车辆
日常多视角拍摄中的临时物体导致3D高斯溅射（3DGS）重建出现鬼影。现有方法依赖场景分解（内存开销大）或运动启发式规则（易受视差模糊影响）。本文提出一种基于语义的过滤框架，利用视觉-语言模型进行类别感知的临时物体去除。通过累积每帧渲染图像与干扰文本提示之间的CLIP相似度得分，对每个高斯点进行评估。超过校准阈值的高斯点被施加透明度正则化并周期性剔除。相比运动方法，该策略独立于运动模式识别物体类别，有效解决视差模糊问题。在RobustNeRF基准的四组序列上，相比原始3DGS，重建质量持续提升，同时保持极低内存开销和实时渲染性能。阈值校准及与基线对比验证了语义引导在可预测干扰类别场景下的实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。