# FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models

arXiv: https://arxiv.org/abs/2303.12786 · HTML: https://mlsanity.com/paper/2303.12786/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 73 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Builds on (most cited first, 30 of 61)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)

## Built on by (most cited first, 30 of 47)

- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [Large Spatial Model: End-to-end Unposed Images to Semantic 3D](https://mlsanity.com/paper/2410.18956/) (2024)
- [LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes](https://mlsanity.com/paper/2410.14462/) (2024)
- [D3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement](https://mlsanity.com/paper/2309.16118/) (2023)
- [DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features](https://mlsanity.com/paper/2406.12095/) (2024)
- [Learning Generalizable Feature Fields for Mobile Manipulation](https://mlsanity.com/paper/2403.07563/) (2024)
- [textitRevelio: Interpreting and leveraging semantic information in diffusion models](https://mlsanity.com/paper/2411.16725/) (2024)
- [Feat2GS: Probing Visual Foundation Models with Gaussian Splatting](https://mlsanity.com/paper/2412.09606/) (2024)
- [GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy](https://mlsanity.com/paper/2410.17488/) (2024)
- [GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow](https://mlsanity.com/paper/2502.17288/) (2025)
- [LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models](https://mlsanity.com/paper/2504.14032/) (2025)
- [GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding](https://mlsanity.com/paper/2311.11863/) (2023)
- [Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D](https://mlsanity.com/paper/2403.18922/) (2024)
- [iSeg: Interactive 3D Segmentation via Interactive Attention](https://mlsanity.com/paper/2404.03219/) (2024)
- [SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields](https://mlsanity.com/paper/2506.09565/) (2025)
- [Customizing Text-to-Image Diffusion with Object Viewpoint Control](https://mlsanity.com/paper/2404.12333/) (2024)
- [LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images](https://mlsanity.com/paper/2507.16144/) (2025)
- [Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving](https://mlsanity.com/paper/2403.05907/) (2024)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [GaussianStego: A Generalizable Stenography Pipeline for Generative 3D Gaussians Splatting](https://mlsanity.com/paper/2407.01301/) (2024)
- [ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images](https://mlsanity.com/paper/2408.17027/) (2024)
- [Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models](https://mlsanity.com/paper/2503.00838/) (2025)
- [DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform](https://mlsanity.com/paper/2501.12637/) (2025)
- [DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations](https://mlsanity.com/paper/2507.19474/) (2025)
- [Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering](https://mlsanity.com/paper/2306.07392/) (2023)
- [Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian](https://mlsanity.com/paper/2408.03516/) (2024)
- [Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model](https://mlsanity.com/paper/2412.13897/) (2024)
- [Semantic Consistent Language Gaussian Splatting for Point-Level Open-vocabulary Querying](https://mlsanity.com/paper/2503.21767/) (2025)
- [Generalizable Neural Human Renderer](https://mlsanity.com/paper/2404.14199/) (2024)

## Abstract (arXiv)

Recent works on generalizable NeRFs have shown promising results on novel view synthesis from single or few images. However, such models have rarely been applied on other downstream tasks beyond synthesis such as semantic understanding and parsing. In this paper, we propose a novel framework named FeatureNeRF to learn generalizable NeRFs by distilling pre-trained vision foundation models (e.g., DINO, Latent Diffusion). FeatureNeRF leverages 2D pre-trained foundation models to 3D space via neural rendering, and then extract deep features for 3D query points from NeRF MLPs. Consequently, it allows to map 2D images to continuous 3D semantic feature volumes, which can be used for various downstream tasks. We evaluate FeatureNeRF on tasks of 2D/3D semantic keypoint transfer and 2D/3D object part segmentation. Our extensive experiments demonstrate the effectiveness of FeatureNeRF as a generalizable 3D semantic feature extractor. Our project page is available at https://jianglongye.com/featurenerf/ .