实时消除虚拟会议中敏感物品，保护用户隐私
A Real-Time Diminished Reality Approach to Privacy in MR Collaboration
- 用语义分割和实时修补技术移除环境中的敏感物体
- 720p下帧率超20fps，支持实时运行
- 无需固定视角或预先扫描，适合移动场景
消减现实（Diminished Reality, DR）指通过合成背景内容来数字移除真实世界物体。本文提出一种实时、基于图像修补的DR系统，用于共享空间混合现实（MR）会议中的隐私控制。系统允许主头显用户选择性移除环境中个人或敏感物品，确保其他参与者无法看到这些物体。移除通过语义分割与精确物体选取实现，随后利用移动ZED 2i深度相机从次级观察者视角进行实时修补，采用YOLOv11进行目标检测，以及改进的解耦时空变换器（DSTT）模型完成高质量视频修补。系统设计便携且鲁棒，无需固定次级视角或环境预先3D扫描。在720p分辨率下，处理管道帧率超过20fps，验证了实时消减现实应用于隐私保护型MR场景的可行性。
原文摘要 · Abstract (English)
Diminished reality (DR) refers to the digital removal of real-world objects by compositing background content in their place. This thesis presents a real-time, inpainting-based DR system designed to enable privacy control in shared-space mixed reality (MR) meetings. The system allows a primary headset user to selectively remove personal or sensitive items from their environment, ensuring that those objects are no longer visible to other participants. Removal is achieved through semantic segmentation and precise object selection, followed by real-time inpainting from the viewpoint of a secondary observer, implemented using a mobile ZED 2i depth camera. The solution is designed to be portable and robust, requiring neither a fixed secondary viewpoint nor prior 3D scanning of the environment. The system utilises YOLOv11 for object detection and a modified Decoupled Spatial-Temporal Transformer (DSTT) model for high-quality video inpainting. At 720p resolution, the pipeline sustains frame rates exceeding 20 fps, demonstrating the feasibility of real-time diminished reality for practical privacy-preserving MR applications.
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。