arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.04075cs.CV
收藏

基于局部表面嵌入的彩色图像三维目标检测及隐目标位姿估计

3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

Univ. Bordeaux(波尔多大学);Bordeaux INP(波尔多国立理工学院);CNRS(法国国家科学研究中心);LaBRI(波尔多计算机科学研究实验室);Siemens Corporate Technology(西门子企业技术部);LIGM(几何与图像实验室);IMAGINE(图像、建模、分析、几何与计算机视觉实验室);Ecole des Ponts(巴黎综合理工学院桥路学院);Univ Gustave Eiffel(古斯塔夫·埃菲尔大学)

Giorgia Pitteri, Aurélie Bugeau, Slobodan Ilic, Vincent Lepetit

摘要:

我们提出了一种用于检测和估计图像中对象的3D姿态的方法,该方法只需要无纹理的CAD模型,并且不需要新对象的训练阶段。我们的方法结合了深度学习和3D几何:它依赖于嵌入局部3D几何来匹配CAD模型和输入图像。对于物体表面的点,这种嵌入可以直接从CAD模型中计算出来;对于图像位置,我们可以从图像本身中预测。这建立了CAD模型上的3D点与输入图像的2D位置之间的对应关系。然而,这些对应关系中的许多是模糊的,因为许多点可能具有相似的局部几何形状。我们表明,我们可以以类不可知的方式使用Mask-RCNN来检测新对象,而无需重新训练,从而大大限制了可能的对应关系的数量。然后,我们可以使用RANSAC类算法从这些区别性对应中鲁棒地估计3D姿态。我们在T-LESS数据集上展示了这种方法的性能,通过使用少量对象来学习嵌入并在其他对象上进行测试。实验结果表明,该方法与已有方法相比,具有较好的性能。

英文摘要:

We present an approach for detecting and estimating the 3D poses of objects in images that requires only an untextured CAD model and no training phase for new objects. Our approach combines Deep Learning and 3D geometry: It relies on an embedding of local 3D geometry to match the CAD models to the input images. For points at the surface of objects, this embedding can be computed directly from the CAD model; for image locations, we learn to predict it from the image itself. This establishes correspondences between 3D points on the CAD model and 2D locations of the input images. However, many of these correspondences are ambiguous as many points may have similar local geometries. We show that we can use Mask-RCNN in a class-agnostic way to detect the new objects without retraining and thus drastically limit the number of possible correspondences. We can then robustly estimate a 3D pose from these discriminative correspondences using a RANSAC- like algorithm. We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects. Our experiments show that our method is on par or better than previous methods.

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。

↑