English

Neural Semantic Surface Maps

Computer Vision and Pattern Recognition 2024-03-11 v3 Graphics

Abstract

We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Lack of annotated data prohibits direct inference of 3D semantic priors; instead, current State-of-the-art methods predominantly optimize geometric properties or require varying amounts of manual annotation. To overcome the lack of annotated training data, we distill semantic matches from pre-trained vision models: our method renders the pair of 3D shapes from multiple viewpoints; the resulting renders are then fed into an off-the-shelf image-matching method which leverages a pretrained visual model to produce feature points. This yields semantic correspondences, which can be projected back to the 3D shapes, producing a raw matching that is inaccurate and inconsistent between different viewpoints. These correspondences are refined and distilled into an inter-surface map by a dedicated optimization scheme, which promotes bijectivity and continuity of the output map. We illustrate that our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement. Furthermore, it proves effective in scenarios with high semantic complexity, where objects are non-isometrically related, as well as in situations where they are nearly isometric.

Keywords

Cite

@article{arxiv.2309.04836,
  title  = {Neural Semantic Surface Maps},
  author = {Luca Morreale and Noam Aigerman and Vladimir G. Kim and Niloy J. Mitra},
  journal= {arXiv preprint arXiv:2309.04836},
  year   = {2024}
}

Comments

Accepted at Eurographics 2024

R2 v1 2026-06-28T12:17:05.620Z