ReScene4D: 时空一致的动态室内3D场景语义实例分割
ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes
AI总结：
ReScene4D提出了一种新的4D室内语义实例分割方法，通过时空对比损失、掩码和序列化技术，在无需密集观测的情况下实现实例跟踪和性能提升，引入t-mAP指标评估时空一致性。
摘要：
室内环境随着物体的移动、出现或离开而演变。捕捉这些动态需要在间歇性捕获的3D扫描之间保持时间一致的实例身份，即使变化未被观测。我们引入并形式化了时空稀疏4D室内语义实例分割（SIS）任务，该任务联合分割、识别和时间关联物体实例。这一设置对现有3DSIS方法构成挑战，因为它们需要离散匹配步骤，而4D激光雷达方法则因依赖高频时间测量而表现不佳。我们提出了ReScene4D，一种新的方法，通过适应3DSIS架构以适应4DSIS，无需密集观测。我们的方法通过时空对比损失、掩码和序列化技术，适应性地利用几何和语义先验。共享上下文使实例跟踪一致，并提高标准3DSIS性能。为评估此任务，我们定义了新的指标t-mAP，扩展mAP以奖励时间身份一致性。ReScene4D在3RScan数据集上实现了最先进的性能，建立了理解动态室内场景的新基准。
英文摘要：
Indoor environments evolve as objects move, appear, or leave the scene. Capturing these dynamics requires maintaining temporally consistent instance identities across intermittently captured 3D scans, even when changes are unobserved. We introduce and formalize the task of temporally sparse 4D indoor semantic instance segmentation (SIS), which jointly segments, identifies, and temporally associates object instances. This setting poses a challenge for existing 3DSIS methods, which require a discrete matching step due to their lack of temporal reasoning, and for 4D LiDAR approaches, which perform poorly due to their reliance on high-frequency temporal measurements that are uncommon in the longer-horizon evolution of indoor environments. We propose ReScene4D, a novel method that adapts 3DSIS architectures for 4DSIS without needing dense observations. Our method enables temporal information sharing--using spatiotemporal contrastive loss, masking, and serialization--to adaptively leverage geometric and semantic priors across observations. This shared context enables consistent instance tracking and improves standard 3DSIS performance. To evaluate this task, we define a new metric, t-mAP, that extends mAP to reward temporal identity consistency. ReScene4D achieves state-of-the-art performance on the 3RScan dataset, establishing a new benchmark for understanding evolving indoor scenes.
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。
