GARField: Group Anything with Radiance Fields

TL;DR

GARField is a novel method that decomposes 3D scenes into hierarchical, semantically meaningful groups by leveraging scale-conditioned affinity fields, enabling multi-level scene understanding from posed images.

Contribution

It introduces a scale-conditioned affinity field approach that captures multi-level scene groupings and respects ambiguity, improving 3D scene decomposition from 2D masks.

Findings

Effectively extracts multi-level scene groups including objects and parts

Produces higher fidelity groups than input masks from SAM

Ensures multi-view consistency in groupings

Abstract

Grouping is inherently ambiguous due to the multiple levels of granularity in which one can decompose a scene -- should the wheels of an excavator be considered separate or part of the whole? We present Group Anything with Radiance Fields (GARField), an approach for decomposing 3D scenes into a hierarchy of semantically meaningful groups from posed image inputs. To do this we embrace group ambiguity through physical scale: by optimizing a scale-conditioned 3D affinity feature field, a point in the world can belong to different groups of different sizes. We optimize this field from a set of 2D masks provided by Segment Anything (SAM) in a way that respects coarse-to-fine hierarchy, using scale to consistently fuse conflicting masks from different viewpoints. From this field we can derive a hierarchy of possible groupings via automatic tree construction or user interaction. We evaluate GARField on a variety of in-the-wild scenes and find it effectively extracts groups at many levels: clusters of objects, objects, and various subparts. GARField inherently represents multi-view consistent groupings and produces higher fidelity groups than the input SAM masks. GARField's hierarchical grouping could have exciting downstream applications such as 3D asset extraction or dynamic scene understanding. See the project website at https://www.garfield.studio/