ProClosure: Hierarchical Room-Object Assignment using Progressive Boundary Closure from Monocular Video

📄 arXiv: 2609.12614v1 📥 PDF

作者: Vinoth Kumar Muthuraj, Soumyadeep Banik, Kushal Sharma, Hardik Jain

分类: cs.RO

发布日期: 2026-09-11

备注: https://github.com/ClarityLab-Org/ProClosure

💡 一句话要点

提出渐进边界闭合方法以解决单目视频中的房间-物体分配问题

🎯 匹配领域: 支柱三：空间感知与语义 (Perception & Semantics)

关键词: 单目视频 房间分配 物体识别 边界闭合 SLAM 结构化点云 机器人导航 智能家居

📋 核心要点

  1. 现有方法在房间和物体分配中面临边界不清晰的问题，导致错误的房间分配和物体检索失败。
  2. 本研究提出通过渐进边界闭合技术，利用相机姿态作为种子，逐步恢复房间结构并进行物体分配，消除传统方法的随机性。
  3. 在10个HM3D-Semantics场景的实验中，房间F1分数从0.741提升至0.890，物体到房间的ARI从0.488提升至0.696，显示出显著的性能改进。

📝 摘要（中文）

本文提出了一种名为渐进边界闭合（Progressive Boundary Closure）的方法，旨在从单目RGB视频中恢复房间层次结构。通过结合SLAM前端和开放词汇分割器，生成结构化点云、相机轨迹和物体轨迹。该方法通过逐步加厚边界并在每个自由空间区域被封闭时冻结，来恢复房间，并将物体分配给其占据大部分的房间。实验结果表明，该方法在多个HM3D-Semantics场景中显著提高了房间的F1分数和物体到房间的ARI。

🔬 方法详解

问题定义：本文旨在解决从单目视频中恢复房间结构及物体分配的问题。现有方法在处理边界模糊时，无法有效区分门口和墙壁，导致房间合并错误。

核心思路：提出渐进边界闭合方法，通过逐步加厚边界并在封闭时冻结区域，来准确恢复房间结构，并将物体分配给占据大部分的房间。相机姿态作为种子，确保分割过程的确定性。

技术框架：整体流程包括SLAM前端生成结构化点云、相机轨迹和物体轨迹，接着将点云栅格化为自上而下的地图，最后通过边界闭合技术恢复房间并分配物体。

关键创新：本研究的创新在于将房间恢复与物体分配结合，通过边界的渐进加厚处理，避免了传统方法对边界的模糊处理，从而实现了更高的准确性。

关键设计：在参数设置上，采用相机姿态作为种子点，消除了随机采样的影响；在损失函数设计上，确保了房间和物体的分配精度，优化了分割结果。整体方法在处理复杂场景时表现出色。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，在10个HM3D-Semantics场景中，使用渐进边界闭合方法恢复了74个房间，房间F1分数从0.741提升至0.890，物体到房间的ARI从0.488提升至0.696，且在每个场景中均表现出一致的性能提升，具有显著的实用价值。

🎯 应用场景

该研究的潜在应用领域包括机器人导航、智能家居和增强现实等。通过准确恢复房间结构和物体分配，机器人能够更有效地执行任务，如物品检索和环境理解，提升用户体验和操作效率。未来，该方法可扩展至更复杂的场景和多模态数据融合，进一步推动智能系统的发展。

📄 摘要（原文）

A 3D scene graph groups objects into rooms. When a robot is asked to fetch an object from the kitchen, that grouping is what tells it where to look. An object recorded in the wrong room is not retrievable by a query naming the correct room. We introduce Progressive Boundary Closure, which recovers room layer from a monocular RGB video. A SLAM front end and an open-vocabulary segmenter supply a structural point cloud, camera trajectory and object tracks. The cloud is rasterised into a top-down map, rooms are recovered from it, and each object takes the room holding most of its extent. The difficulty lies in the map itself. Walls are recorded only where the camera looked, so a gap in the boundary may be a doorway or a stretch of wall that was never observed; nothing distinguishes the two. Prior methods treat both as passages, merging rooms that should remain separate. We observe that both require the same treatment: a room should not extend across either, so both are closed and need not be distinguished. Such an opening closes under a small amount of boundary growth, and few sightlines cross it, so points in different rooms rarely see one another. We use the first to recover rooms and the second to assign objects to them. Rooms are obtained by Progressively thickening the boundary inward and freezing each free-space region once it becomes enclosed, so every opening seals at its own scale rather than at a radius fixed in advance. Camera poses are used as seeds, which removes the sampling heuristic and makes the segmentation deterministic. Over 10 floors of 6 HM3D-Semantics scenes, scored against HOV-SG on identical top-down maps, we recover 74 rooms for 72 annotated regions (HOV-SG: 44), raising room F_1 from 0.741 to 0.890 at IoU 0.25 at some cost in precision, and object-to-room ARI from 0.488 to 0.696 (p=0.002, ahead on every floor).