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

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 CVPR 2017 PDF CVPR 2017 Abstract

Datasets


Introduced in the Paper:

3DMatch

Mentioned in the Paper:

ImageNet SUN3D Scan2CAD

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Point Cloud Registration 3DMatch Benchmark 3DMatch + RANSAC Recall 66.8 # 9
3D Reconstruction Scan2CAD 3DMatch Average Accuracy 10.29% # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet