Timezone: »

Neural Feature Matching in Implicit 3D Representations
Yunlu Chen · Basura Fernando · Hakan Bilen · Thomas Mensink · Efstratios Gavves

Thu Jul 22 07:45 AM -- 07:50 AM (PDT) @

Recently, neural implicit functions have achieved impressive results for encoding 3D shapes. Conditioning on low-dimensional latent codes generalises a single implicit function to learn shared representation space for a variety of shapes, with the advantage of smooth interpolation. While the benefits from the global latent space do not correspond to explicit points at local level, we propose to track the continuous point trajectory by matching implicit features with the latent code interpolating between shapes, from which we corroborate the hierarchical functionality of the deep implicit functions, where early layers map the latent code to fitting the coarse shape structure, and deeper layers further refine the shape details. Furthermore, the structured representation space of implicit functions enables to apply feature matching for shape deformation, with the benefits to handle topology and semantics inconsistency, such as from an armchair to a chair with no arms, without explicit flow functions or manual annotations.

Author Information

Yunlu Chen (University of Amsterdam)
Basura Fernando (Agency for Science, Technology and Research (A*STAR))
Hakan Bilen (University of Edinburgh)
Thomas Mensink (Google Research / University of Amsterdam)
Efstratios Gavves (University of Amsterdam )

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors