3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

CVPR 2017 Andy ZengShuran SongMatthias NießnerMatthew FisherJianxiong XiaoThomas Funkhouser

Matching local geometric features on real-world depth images is a challenging task due to the noisy, low-resolution, and incomplete nature of 3D scan data. These difficulties limit the performance of current state-of-art methods, which are typically based on histograms over geometric properties... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
3D Reconstruction Scan2CAD 3DMatch Average Accuracy 10.29% # 2