# Learning Neural Duplex Radiance Fields for Real-Time View Synthesis

arXiv: https://arxiv.org/abs/2304.10537 · HTML: https://mlsanity.com/paper/2304.10537/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 61 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 30 of 51)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [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)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures](https://mlsanity.com/paper/2208.00277/) (2022)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks](https://mlsanity.com/paper/2103.03231/) (2021)
- [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020)

## Built on by (most cited first, 28 of 28)

- [3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting](https://mlsanity.com/paper/2412.12507/) (2024)
- [VR-NeRF: High-Fidelity Virtualized Walkable Spaces](https://mlsanity.com/paper/2311.02542/) (2023)
- [SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration](https://mlsanity.com/paper/2312.07541/) (2023)
- [Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes](https://mlsanity.com/paper/2310.08585/) (2023)
- [EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis](https://mlsanity.com/paper/2410.01804/) (2024)
- [Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos](https://mlsanity.com/paper/2403.17103/) (2024)
- [VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams](https://mlsanity.com/paper/2312.01407/) (2023)
- [CAD: Photorealistic 3D Generation via Adversarial Distillation](https://mlsanity.com/paper/2312.06663/) (2023)
- [City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web](https://mlsanity.com/paper/2312.16457/) (2023)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation](https://mlsanity.com/paper/2310.05391/) (2023)
- [LightSpeed: Light and Fast Neural Light Fields on Mobile Devices](https://mlsanity.com/paper/2310.16832/) (2023)
- [SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields](https://mlsanity.com/paper/2409.04482/) (2024)
- [Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations](https://mlsanity.com/paper/2310.17880/) (2023)
- [Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes](https://mlsanity.com/paper/2409.02482/) (2024)
- [RaFE: Generative Radiance Fields Restoration](https://mlsanity.com/paper/2404.03654/) (2024)
- [Analyzing the Internals of Neural Radiance Fields](https://mlsanity.com/paper/2306.00696/) (2023)
- [EG-HumanNeRF: Efficient Generalizable Human NeRF Utilizing Human Prior for Sparse View](https://mlsanity.com/paper/2410.12242/) (2024)
- [Oblique-MERF: Revisiting and Improving MERF for Oblique Photography](https://mlsanity.com/paper/2404.09531/) (2024)
- [MomentsNeRF: Leveraging Orthogonal Moments for Few-Shot Neural Rendering](https://mlsanity.com/paper/2407.02668/) (2024)
- [NGP-RT: Fusing Multi-Level Hash Features with Lightweight Attention for Real-Time Novel View Synthesis](https://mlsanity.com/paper/2407.10482/) (2024)
- [Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction](https://mlsanity.com/paper/2505.19793/) (2025)
- [Baking Relightable NeRF for Real-time Direct/Indirect Illumination Rendering](https://mlsanity.com/paper/2409.10327/) (2024)
- [Disentangled 4D Gaussian Splatting: Rendering High-Resolution Dynamic World at 343 FPS](https://mlsanity.com/paper/2503.22159/) (2025)
- [Probabilistic Directed Distance Fields for Ray-Based Shape Representations](https://mlsanity.com/paper/2404.09081/) (2024)
- [Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives](https://mlsanity.com/paper/2411.19903/) (2024)
- [Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency](https://mlsanity.com/paper/2505.18932/) (2025)
- [Recent Advances and Trends in Learning-based 3D Representations](https://mlsanity.com/paper/2606.04871/) (2026)

## Abstract (arXiv)

Neural radiance fields (NeRFs) enable novel view synthesis with unprecedented visual quality. However, to render photorealistic images, NeRFs require hundreds of deep multilayer perceptron (MLP) evaluations - for each pixel. This is prohibitively expensive and makes real-time rendering infeasible, even on powerful modern GPUs. In this paper, we propose a novel approach to distill and bake NeRFs into highly efficient mesh-based neural representations that are fully compatible with the massively parallel graphics rendering pipeline. We represent scenes as neural radiance features encoded on a two-layer duplex mesh, which effectively overcomes the inherent inaccuracies in 3D surface reconstruction by learning the aggregated radiance information from a reliable interval of ray-surface intersections. To exploit local geometric relationships of nearby pixels, we leverage screen-space convolutions instead of the MLPs used in NeRFs to achieve high-quality appearance. Finally, the performance of the whole framework is further boosted by a novel multi-view distillation optimization strategy. We demonstrate the effectiveness and superiority of our approach via extensive experiments on a range of standard datasets.