Do We Need Binary Features for 3D Reconstruction?

  title={Do We Need Binary Features for 3D Reconstruction?},
  author={Bin Fan and Qingqun Kong and Wei Sui and Zhiheng Wang and Xinchao Wang and Shiming Xiang and Chunhong Pan and P. Fua},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Bin Fan, Qingqun Kong, +5 authors P. Fua
  • Published 2016
  • Computer Science, Mathematics
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors. They have been shown with promising results on some real time applications, e.g., SLAM, where the matching operations are relative few. However, in computer vision, there are many applications such as 3D reconstruction requiring lots of matching operations between local features. Therefore, a natural question is… Expand
A Performance Evaluation of Local Features for Image-Based 3D Reconstruction
Beyond SIFT using binary features in Loop Closure Detection
Information Theoretic Rotationwise Robust Binary Descriptor Learning
Learning Latent Features With Infinite Nonnegative Binary Matrix Trifactorization


BRISK: Binary Robust invariant scalable keypoints
Comparative Evaluation of Binary Features
Fast Matching of Binary Features
  • Marius Muja, D. Lowe
  • Mathematics, Computer Science
  • 2012 Ninth Conference on Computer and Robot Vision
  • 2012
FREAK: Fast Retina Keypoint
Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction
Interesting Interest Points
Thick boundaries in binary space and their influence on nearest-neighbor search
Machine Learning for High-Speed Corner Detection
Evaluation of local detectors and descriptors for fast feature matching
  • O. Miksik, K. Mikolajczyk
  • Computer Science
  • Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
  • 2012
Accurate, Dense, and Robust Multiview Stereopsis