pith. sign in

arxiv: 2406.04309 · v1 · pith:XRW7XDWYnew · submitted 2024-06-06 · 💻 cs.CV · cs.GR· cs.LG· cs.MM

ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation

classification 💻 cs.CV cs.GRcs.LGcs.MM
keywords recursivecontinuousfieldformulationlatentmemorymulti-scenemultiple
0
0 comments X
read the original abstract

The common trade-offs of state-of-the-art methods for multi-shape representation (a single model "packing" multiple objects) involve trading modeling accuracy against memory and storage. We show how to encode multiple shapes represented as continuous neural fields with a higher degree of precision than previously possible and with low memory usage. Key to our approach is a recursive hierarchical formulation that exploits object self-similarity, leading to a highly compressed and efficient shape latent space. Thanks to the recursive formulation, our method supports spatial and global-to-local latent feature fusion without needing to initialize and maintain auxiliary data structures, while still allowing for continuous field queries to enable applications such as raytracing. In experiments on a set of diverse datasets, we provide compelling qualitative results and demonstrate state-of-the-art multi-scene reconstruction and compression results with a single network per dataset.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.