N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
This addresses the problem of multi-level scene understanding in computer vision, offering a flexible and comprehensive approach that is incremental in its method.
The paper tackles the challenge of understanding complex scenes at multiple abstraction levels by introducing Nested Neural Feature Fields (N2F2), which uses hierarchical supervision to learn a single feature field encoding scene properties at varying granularities, resulting in outperforming state-of-the-art methods on tasks like open-vocabulary 3D segmentation and localization.
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 and nuanced understanding of scenes. We leverage a 2D class-agnostic segmentation model to provide semantically meaningful pixel groupings at arbitrary scales in the image space, and query the CLIP vision-encoder to obtain language-aligned embeddings for each of these segments. Our proposed hierarchical supervision method then assigns different nested dimensions of the feature field to distill the CLIP embeddings using deferred volumetric rendering at varying physical scales, creating a coarse-to-fine representation. Extensive experiments show that our approach outperforms the state-of-the-art feature field distillation methods on tasks such as open-vocabulary 3D segmentation and localization, demonstrating the effectiveness of the learned nested feature field.