N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields

arXiv:2403.10997v1 Announce Type: cross
Abstract: Understanding complex scenes at multiple levels of abstraction remains a formidable challenge in computer vision. To address this, we introduce Nested Neural Feature Fields (N2F2), a novel approach that employs hierarchical supervision to learn a single feature field, wherein different dimensions within the same high-dimensional feature encode scene properties at varying granularities. Our method allows for a flexible definition of hierarchies, tailored to either the physical dimensions or semantics or both, thereby enabling a comprehensive …

abstract abstraction arxiv challenge computer computer vision cs.ai cs.cv cs.gr cs.lg dimensions feature fields hierarchical learn multiple novel supervision type understanding vision