# DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features

arXiv: https://arxiv.org/abs/2406.12095 · HTML: https://mlsanity.com/paper/2406.12095/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 61 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)

## Built on by (most cited first, 30 of 33)

- [STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes](https://mlsanity.com/paper/2501.00602/) (2024)
- [DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input](https://mlsanity.com/paper/2409.12753/) (2024)
- [GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding](https://mlsanity.com/paper/2412.13193/) (2024)
- [SPA: 3D Spatial-Awareness Enables Effective Embodied Representation](https://mlsanity.com/paper/2410.08208/) (2024)
- [DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving](https://mlsanity.com/paper/2601.01528/) (2026)
- [DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion](https://mlsanity.com/paper/2510.15264/) (2025)
- [Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking](https://mlsanity.com/paper/2510.10287/) (2025)
- [Self-Supervised Sparse Sensor Fusion for Long Range Perception](https://mlsanity.com/paper/2508.13995/) (2025)
- [VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction](https://mlsanity.com/paper/2510.19578/) (2025)
- [Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving](https://mlsanity.com/paper/2506.12251/) (2025)
- [VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2510.23205/) (2025)
- [OccAny: Generalized Unconstrained Urban 3D Occupancy](https://mlsanity.com/paper/2603.23502/) (2026)
- [Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives](https://mlsanity.com/paper/2505.09074/) (2025)
- [OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving](https://mlsanity.com/paper/2512.14225/) (2025)
- [Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction](https://mlsanity.com/paper/2510.04759/) (2025)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)
- [See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction](https://mlsanity.com/paper/2505.20641/) (2025)
- [ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding](https://mlsanity.com/paper/2512.03370/) (2025)
- [UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling](https://mlsanity.com/paper/2602.20943/) (2026)
- [Test-Time 3D Occupancy Prediction](https://mlsanity.com/paper/2503.08485/) (2025)
- [DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting](https://mlsanity.com/paper/2504.10486/) (2025)
- [Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception](https://mlsanity.com/paper/2509.26087/) (2025)
- [QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy](https://mlsanity.com/paper/2511.17221/) (2025)
- [To View Transform or Not to View Transform: NeRF-based Pre-training Perspective](https://mlsanity.com/paper/2603.28090/) (2026)
- [sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views](https://mlsanity.com/paper/2502.04318/) (2025)
- [DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation](https://mlsanity.com/paper/2510.24261/) (2025)
- [OccLE: Label-Efficient 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2505.20617/) (2025)
- [SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering](https://mlsanity.com/paper/2511.17361/) (2025)
- [HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction](https://mlsanity.com/paper/2512.19871/) (2025)
- [From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving](https://mlsanity.com/paper/2605.01995/) (2026)

## Abstract (arXiv)

We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in outdoor autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs with limited view overlap, and is trained self-supervised with differentiable rendering to reconstruct RGB, depth, or feature images. Our first insight is to exploit per-scene optimized Neural Radiance Fields (NeRFs) by generating dense depth and virtual camera targets from them, which helps our model to learn enhanced 3D geometry from sparse non-overlapping image inputs. Second, to learn a semantically rich 3D representation, we propose distilling features from pre-trained 2D foundation models, such as CLIP or DINOv2, thereby enabling various downstream tasks without the need for costly 3D human annotations. To leverage these two insights, we introduce a novel model architecture with a two-stage lift-splat-shoot encoder and a parameterized sparse hierarchical voxel representation. Experimental results on the NuScenes and Waymo NOTR datasets demonstrate that DistillNeRF significantly outperforms existing comparable state-of-the-art self-supervised methods for scene reconstruction, novel view synthesis, and depth estimation; and it allows for competitive zero-shot 3D semantic occupancy prediction, as well as open-world scene understanding through distilled foundation model features. Demos and code will be available at https://distillnerf.github.io/.