English

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

Computer Vision and Pattern Recognition 2024-06-07 v1 Graphics Machine Learning Multimedia

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.

Keywords

Cite

@article{arxiv.2406.04309,
  title  = {ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation},
  author = {Sergey Zakharov and Katherine Liu and Adrien Gaidon and Rares Ambrus},
  journal= {arXiv preprint arXiv:2406.04309},
  year   = {2024}
}

Comments

SIGGRAPH 2024. Project Page: https://zakharos.github.io/projects/refine/

R2 v1 2026-06-28T16:56:16.976Z