Deep orientation-aware functional maps: Tackling symmetry issues in Shape Matching

State-of-the-art fully intrinsic network for non-rigid shape matching are unable to disambiguate between shape inner symmetries. Meanwhile, recent advances in the functional map framework allow to enforce orientation preservation using a functional representation for tangent vector field transfer, t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 732 - 741
Hlavní autoři: Donati, Nicolas, Corman, Etienne, Ovsjanikov, Maks
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
Codes
Computer architecture
Computer vision
Deep learning
Deep learning architectures and techniques; Segmentation
grouping and shape analysis
Pattern matching
Shape
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:State-of-the-art fully intrinsic network for non-rigid shape matching are unable to disambiguate between shape inner symmetries. Meanwhile, recent advances in the functional map framework allow to enforce orientation preservation using a functional representation for tangent vector field transfer, through so-called complex functional maps. Using this representation, we propose a new deep learning approach to learn orientation-aware features in afully unsupervised setting. Our architecture is built on DiffusionNet, which makes our method robust to discretization changes, while adding a vector-field-based loss, which promotes orientation preservation without using (often unstable) extrinsic descriptors. Our source code is available at: https://github.com/nicolasdonati/DUO-FM.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00082