Learning local descriptors with adversarial enhancer from volumetric geometry patches

Jing Zhu, Yi Fang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Local matching problems (e.g. key point matching, geometry registration) are significant but challenging tasks in computer vision field. In this paper, we propose to learn a robust local 3D descriptor from volumetric point patches to tackle the local matching tasks. Intuitively, given two inputs, it would be easy for a network to map the inputs to a space with similar characteristics (e.g. similar outputs for similar inputs, far different outputs for far different inputs), but the difficult case for a network would be to map the inputs into a space with opposite characteristics (e.g. far different outputs for very similar inputs but very similar outputs for far different inputs). Inspired by this intuition, in our proposed method, we design a siamese-network-based local descriptor generator to learn a local descriptor with small distances between match pairs and large distances between non-match pairs. Specifically, an adversarial enhancer is introduced to map the outputs of the local descriptor generator into an opposite space that match pairs have the maximum differences and non-match pairs have the minimum differences. The local descriptor generator and the adversarial enhancer are trained in an adversarial manner. By competing with the adversarial enhancer, the local descriptor generator learns to generate a much stronger descriptor for given volumetric point patches. The experiments conducted on real-world scan datasets, including 7-scenes and SUN3D, and the synthetic scan augmented ICL-NUIM dataset show that our method can achieve superior performance over other state-of-the-art approaches on both keypoint matching and geometry registration, such as fragment alignment and scene reconstruction.

Original languageEnglish (US)
Title of host publicationMM 2018 - Proceedings of the 2018 ACM Multimedia Conference
PublisherAssociation for Computing Machinery, Inc
Number of pages9
ISBN (Electronic)9781450356657
StatePublished - Oct 15 2018
Event26th ACM Multimedia conference, MM 2018 - Seoul, Korea, Republic of
Duration: Oct 22 2018Oct 26 2018

Publication series

NameMM 2018 - Proceedings of the 2018 ACM Multimedia Conference


Other26th ACM Multimedia conference, MM 2018
Country/TerritoryKorea, Republic of


  • Adversarial learning
  • Geometry registration
  • Keypoint matching

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction


Dive into the research topics of 'Learning local descriptors with adversarial enhancer from volumetric geometry patches'. Together they form a unique fingerprint.

Cite this