RelationField: Relate Anything in Radiance Fields
This addresses a gap in 3D scene understanding for applications like robotics and AR/VR, though it is incremental as it builds on existing neural radiance field methods.
The paper tackles the problem of understanding semantic relationships between objects in neural radiance fields, which was previously unexplored, by proposing RelationField to extract inter-object relationships directly from these fields, achieving state-of-the-art performance in open-vocabulary 3D scene graph generation and relationship-guided instance segmentation.
Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from vision-language models. However, current method primarily focus on object-centric representations, supporting object segmentation or detection, while understanding semantic relationships between objects remains largely unexplored. To address this gap, we propose RelationField, the first method to extract inter-object relationships directly from neural radiance fields. RelationField represents relationships between objects as pairs of rays within a neural radiance field, effectively extending its formulation to include implicit relationship queries. To teach RelationField complex, open-vocabulary relationships, relationship knowledge is distilled from multi-modal LLMs. To evaluate RelationField, we solve open-vocabulary 3D scene graph generation tasks and relationship-guided instance segmentation, achieving state-of-the-art performance in both tasks. See the project website at https://relationfield.github.io.