@inproceedings{18244,
  abstract     = {Some face recognition methods are designed to utilize geometric information extracted from depth sensors to overcome the weaknesses of single-image based recognition technologies. However, the accurate acquisition of the depth profile is an expensive and challenging process. Here, we introduce a novel method that learns to recognize faces from stereo camera systems without the need to explicitly compute the facial surface or depth map. The raw face stereo images along with the location in the image from which the face is extracted allow the proposed CNN to improve the recognition task while avoiding the need to explicitly handle the geometric structure of the face. This way, we keep the simplicity and cost efficiency of identity authentication from a single image, while enjoying the benefits of geometric data without explicitly reconstructing it. We demonstrate that the suggested method outperforms both existing single-image and explicit depth based methods on largescale benchmarks, and even capable of recognize spoofing attacks. We also provide an ablation study that shows that the suggested method uses the face locations in the left and right images to encode informative features that improve the overall performance.},
  author       = {Livne, Amir and Aviv, Ziv and Grofit, Shahaf and Bronstein, Alexander and Kimmel, Ron},
  booktitle    = {2020 International Conference on 3D Vision (3DV)},
  isbn         = {9781728181295},
  issn         = {2475-7888},
  location     = {Fukuoka, Japan},
  publisher    = {IEEE},
  title        = {{Do we need depth in state-uf-the-art face authentication?}},
  doi          = {10.1109/3dv50981.2020.00099},
  year         = {2021},
}

@inproceedings{18257,
  abstract     = {We consider the problem of localizing relevant subsets of non-rigid geometric shapes given only a partial 3D query as the input. Such problems arise in several challenging tasks in 3D vision and graphics, including partial shape similarity, retrieval, and non-rigid correspondence. We phrase the problem as one of alignment between short sequences of eigenvalues of basic differential operators, which are constructed upon a scalar function defined on the 3D surfaces. Our method therefore seeks for a scalar function that entails this alignment. Differently from existing approaches, we do not require solving for a correspondence between the query and the target, therefore greatly simplifying the optimization process; our core technique is also descriptor-free, as it is driven by the geometry of the two objects as encoded in their operator spectra. We further show that our spectral alignment algorithm provides a remarkably simple alternative to the recent shape-from-spectrum reconstruction approaches. For both applications, we demonstrate improvement over the state-of-the-art either in terms of accuracy or computational cost.},
  author       = {Rampini, Arianna and Tallini, Irene and Ovsjanikov, Maks and Bronstein, Alexander and Rodola, Emanuele},
  booktitle    = {2019 International Conference on 3D Vision (3DV)},
  isbn         = {9781728131320},
  issn         = {2475-7888},
  location     = {Quebec City, QC, Canada},
  publisher    = {IEEE},
  title        = {{Correspondence-free region localization for partial shape similarity via Hamiltonian spectrum alignment}},
  doi          = {10.1109/3dv.2019.00014},
  year         = {2019},
}