发表机构
University of Houston（休斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有镜面检测仅关注单图像的局限，提出多视图镜面检测方法MVMD及首个多视图镜面检测数据库，通过三个模块提升检测效果，使准确率和IoU分别最高提升2.6%和11.1%，增强了镜面密集环境下的三维重建准确性。
AI 中文摘要
在三维重建中，镜面会产生扭曲和碎片化的空间，从而导致三维模型不准确且不可靠。由于三维重建通常依赖多视图图像来捕捉场景的不同视角，因此在重建前检测并标记多视图图像中的镜面可有效解决该问题。然而，现有方法仅关注单图像检测，忽略了多视图设置提供的丰富信息。为克服这一局限，我们提出了一种新型多视图镜面检测方法MVMD，以及首个专为多视图场景中镜面检测设计的数据库。MVMD的设计基于不同视角观察到的物体与镜内、镜外物体之间的固有关联，这些关联通过交叉注意力和自注意力机制进行学习。MVMD包含三个关键模块：跨视图模块跟踪因视角变化导致的镜内物体偏移；视图内模块检测镜内的物体反射；细化模块锐化镜面边界并增强检测细节。实验结果表明，与单图像镜面检测技术相比，我们的方法准确率最高提升2.6%，交并比（IoU）最高提升11.1%。这一显著提升使MVMD对计算机视觉任务尤为有效，尤其是在镜面密集环境中提高三维重建的准确性。
英文摘要
In 3D reconstruction, mirrors introduce significant challenges by creating distorted and fragmented spaces, resulting in inaccurate and unreliable 3D models. As 3D reconstruction typically relies on multi-view images to capture different perspectives of a scene, detecting and labeling mirrors in multi-view images before reconstruction can effectively address this issue. However, existing methods focus solely on single-image detection, overlooking the rich information provided by multi-view setups. To overcome this limitation, we propose MVMD, a novel Multi-View Mirror Detection method, along with the first database specifically designed for mirror detection in multi-view scenes. The design of MVMD is grounded in the inherent associations between objects seen from different views and those reflected inside and outside of mirrors. These relationships are learned through cross- and self-attention mechanisms. MVMD consists of three key blocks: the Inter-Views Block tracks the shifts of objects within mirrors caused by changes in viewpoint; the Intra-View Block detects object reflections inside mirrors; and the Refinement Block sharpens mirror boundaries and enhances detected details. Experimental results show that our method improves accuracy by up to 2.6% and IoU by up to 11.1%, compared to single-image mirror detection techniques. This substantial improvement makes MVMD particularly effective for computer vision tasks, especially in enhancing the accuracy of 3D reconstruction in mirror-dense environments.
CommentsThis work has already published at WACV 2025, just want more accessibility
Journal ref2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
DOI：10.1109/WACV61041.2025.00904
