# N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields

arXiv: https://arxiv.org/abs/2403.10997 · HTML: https://mlsanity.com/paper/2403.10997/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 64 references that are in the map.
- First posted on arXiv 16 Mar 2024.

## Builds on (most cited first, 30 of 56)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)

## Built on by (most cited first, 30 of 34)

- [PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models](https://mlsanity.com/paper/2412.18608/) (2024)
- [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://mlsanity.com/paper/2405.10255/) (2024)
- [Gaga: Group Any Gaussians via 3D-aware Memory Bank](https://mlsanity.com/paper/2404.07977/) (2024)
- [AutoPartGen: Autogressive 3D Part Generation and Discovery](https://mlsanity.com/paper/2507.13346/) (2025)
- [Search3D: Hierarchical Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2409.18431/) (2024)
- [SplatTalk: 3D VQA with Gaussian Splatting](https://mlsanity.com/paper/2503.06271/) (2025)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting](https://mlsanity.com/paper/2412.13654/) (2024)
- [Occam's LGS: An Efficient Approach for Language Gaussian Splatting](https://mlsanity.com/paper/2412.01807/) (2024)
- [PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding](https://mlsanity.com/paper/2503.18107/) (2025)
- [Tackling View-Dependent Semantics in 3D Language Gaussian Splatting](https://mlsanity.com/paper/2505.24746/) (2025)
- [GSemSplat: Generalizable Semantic 3D Gaussian Splatting from Uncalibrated Image Pairs](https://mlsanity.com/paper/2412.16932/) (2024)
- [COS3D: Collaborative Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.20238/) (2025)
- [Splat Feature Solver](https://mlsanity.com/paper/2508.12216/) (2025)
- [OpenSU3D: Open World 3D Scene Understanding using Foundation Models](https://mlsanity.com/paper/2407.14279/) (2024)
- [OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion](https://mlsanity.com/paper/2510.18253/) (2025)
- [3D-Aware Instance Segmentation and Tracking in Egocentric Videos](https://mlsanity.com/paper/2408.09860/) (2024)
- [OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding](https://mlsanity.com/paper/2508.01150/) (2025)
- [OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields](https://mlsanity.com/paper/2510.21441/) (2025)
- [LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds](https://mlsanity.com/paper/2603.24146/) (2026)
- [Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting](https://mlsanity.com/paper/2411.15193/) (2024)
- [ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail](https://mlsanity.com/paper/2503.17044/) (2025)
- [EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation](https://mlsanity.com/paper/2606.08980/) (2026)
- [Point2Act: Efficient 3D Distillation of Multimodal LLMs for Zero-Shot Context-Aware Grasping](https://mlsanity.com/paper/2508.03099/) (2025)
- [B3-Seg: Camera-Free, Training-Free 3DGS Segmentation via Analytic EIG and Beta-Bernoulli Bayesian Updates](https://mlsanity.com/paper/2602.17134/) (2026)
- [Online Segment 3D Gaussians via Launching Virtual Drones](https://mlsanity.com/paper/2607.01628/) (2026)
- [DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos](https://mlsanity.com/paper/2503.08344/) (2025)
- [Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos](https://mlsanity.com/paper/2506.05546/) (2025)
- [PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks](https://mlsanity.com/paper/2509.25970/) (2025)
- [TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding](https://mlsanity.com/paper/2604.03309/) (2026)

## Abstract (arXiv)

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.