# Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision

arXiv: https://arxiv.org/abs/2303.03361 · HTML: https://mlsanity.com/paper/2303.03361/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 63 references that are in the map.
- First posted on arXiv 6 Mar 2023.

## Builds on (most cited first, 30 of 54)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)

## Built on by (most cited first, 30 of 44)

- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding](https://mlsanity.com/paper/2311.18482/) (2023)
- [HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving](https://mlsanity.com/paper/2412.01718/) (2024)
- [Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes](https://mlsanity.com/paper/2303.13450/) (2023)
- [SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving](https://mlsanity.com/paper/2306.09001/) (2023)
- [GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning](https://mlsanity.com/paper/2312.11461/) (2023)
- [EPIC Fields: Marrying 3D Geometry and Video Understanding](https://mlsanity.com/paper/2306.08731/) (2023)
- [Flexible Techniques for Differentiable Rendering with 3D Gaussians](https://mlsanity.com/paper/2308.14737/) (2023)
- [Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields](https://mlsanity.com/paper/2306.12760/) (2023)
- [Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing](https://mlsanity.com/paper/2312.03763/) (2023)
- [Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis](https://mlsanity.com/paper/2304.12317/) (2023)
- [Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling](https://mlsanity.com/paper/2405.14847/) (2024)
- [DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos](https://mlsanity.com/paper/2405.17705/) (2024)
- [RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes](https://mlsanity.com/paper/2403.09419/) (2024)
- [LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes](https://mlsanity.com/paper/2405.00900/) (2024)
- [PointNeRF++: A multi-scale, point-based Neural Radiance Field](https://mlsanity.com/paper/2312.02362/) (2023)
- [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)
- [CF3: Compact and Fast 3D Feature Fields](https://mlsanity.com/paper/2508.05254/) (2025)
- [PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes](https://mlsanity.com/paper/2309.10815/) (2023)
- [Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review](https://mlsanity.com/paper/2402.11141/) (2024)
- [ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images](https://mlsanity.com/paper/2408.17027/) (2024)
- [PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2305.16914/) (2023)
- [UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation](https://mlsanity.com/paper/2411.19292/) (2024)
- [Factored Neural Representation for Scene Understanding](https://mlsanity.com/paper/2304.10950/) (2023)
- [3D StreetUnveiler with Semantic-aware 2DGS -- a simple baseline](https://mlsanity.com/paper/2405.18416/) (2024)
- [ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field](https://mlsanity.com/paper/2401.08140/) (2024)
- [Neural Graph Map: Dense Mapping with Efficient Loop Closure Integration](https://mlsanity.com/paper/2405.03633/) (2024)
- [MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering](https://mlsanity.com/paper/2407.02668/) (2024)

## Abstract (arXiv)

We address efficient and structure-aware 3D scene representation from images. Nerflets are our key contribution -- a set of local neural radiance fields that together represent a scene. Each nerflet maintains its own spatial position, orientation, and extent, within which it contributes to panoptic, density, and radiance reconstructions. By leveraging only photometric and inferred panoptic image supervision, we can directly and jointly optimize the parameters of a set of nerflets so as to form a decomposed representation of the scene, where each object instance is represented by a group of nerflets. During experiments with indoor and outdoor environments, we find that nerflets: (1) fit and approximate the scene more efficiently than traditional global NeRFs, (2) allow the extraction of panoptic and photometric renderings from arbitrary views, and (3) enable tasks rare for NeRFs, such as 3D panoptic segmentation and interactive editing.