通过深度感知与纹理恢复提升人物接触检测精度
Precision-Enhanced Human-Object Contact Detection via Depth-Aware Perspective Interaction and Object Texture Restoration
- 利用深度图生成模型捕捉视角交互信息，避免遮挡导致误检
- 结合掩码膨胀与物体修复技术，还原遮挡区域纹理与边界
- 聚焦接触点附近特征，适合复杂交互场景的检测任务
人体-物体接触（HOT）检测旨在精确识别人体与物体间的接触区域。现有方法在物体频繁遮挡视线时表现不佳，导致接触区域识别不准。为此，本文提出一种基于视角交互的深度感知检测器PIHOT，利用深度图生成模型获取人体与物体相对于相机的深度信息，有效防止误判。同时，采用掩码膨胀与物体纹理修复技术，恢复被遮挡区域的细节，改善物体间边界，增强对交互行为的感知能力。此外，引入空间感知机制，聚焦接触点附近的特征。实验表明，PIHOT在三个基准数据集上均达到领先性能：相比最新方法DHOT，SC-Acc.、C-Acc.、mIoU和wIoU分别提升13%、27.5%、16%和18.5%。
原文摘要 · Abstract (English)
Human-object contact (HOT) is designed to accurately identify the areas where humans and objects come into contact. Current methods frequently fail to account for scenarios where objects are frequently blocking the view, resulting in inaccurate identification of contact areas. To tackle this problem, we suggest using a perspective interaction HOT detector called PIHOT, which utilizes a depth map generation model to offer depth information of humans and objects related to the camera, thereby preventing false interaction detection. Furthermore, we use mask dilatation and object restoration techniques to restore the texture details in covered areas, improve the boundaries between objects, and enhance the perception of humans interacting with objects. Moreover, a spatial awareness perception is intended to concentrate on the characteristic features close to the points of contact. The experimental results show that the PIHOT algorithm achieves state-of-the-art performance on three benchmark datasets for HOT detection tasks. Compared to the most recent DHOT, our method enjoys an average improvement of 13%, 27.5%, 16%, and 18.5% on SC-Acc., C-Acc., mIoU, and wIoU metrics, respectively.
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。