# LightSpeed: Light and Fast Neural Light Fields on Mobile Devices

arXiv: https://arxiv.org/abs/2310.16832 · HTML: https://mlsanity.com/paper/2310.16832/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 29 of 29)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures](https://mlsanity.com/paper/2208.00277/) (2022)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks](https://mlsanity.com/paper/2103.03231/) (2021)
- [BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis](https://mlsanity.com/paper/2302.14859/) (2023)
- [AutoInt: Automatic Integration for Fast Neural Volume Rendering](https://mlsanity.com/paper/2012.01714/) (2020)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement](https://mlsanity.com/paper/2303.02091/) (2023)
- [Extreme View Synthesis](https://mlsanity.com/paper/1812.04777/) (2018)
- [ReLU Fields: The Little Non-linearity That Could](https://mlsanity.com/paper/2205.10824/) (2022)
- [R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis](https://mlsanity.com/paper/2203.17261/) (2022)
- [Learning to Synthesize a 4D RGBD Light Field from a Single Image](https://mlsanity.com/paper/1708.03292/) (2017)
- [NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes](https://mlsanity.com/paper/2303.09431/) (2023)
- [Learning Neural Light Fields with Ray-Space Embedding Networks](https://mlsanity.com/paper/2112.01523/) (2021)
- [Real-Time Neural Light Field on Mobile Devices](https://mlsanity.com/paper/2212.08057/) (2022)
- [NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field](https://mlsanity.com/paper/2105.07112/) (2021)
- [Learning Neural Duplex Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2304.10537/) (2023)
- [Re-ReND: Real-time Rendering of NeRFs across Devices](https://mlsanity.com/paper/2303.08717/) (2023)
- [Progressively-connected Light Field Network for Efficient View Synthesis](https://mlsanity.com/paper/2207.04465/) (2022)

## Built on by (most cited first, 8 of 8)

- [SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration](https://mlsanity.com/paper/2312.07541/) (2023)
- [Lightweight Predictive 3D Gaussian Splats](https://mlsanity.com/paper/2406.19434/) (2024)
- [CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenes](https://mlsanity.com/paper/2409.05166/) (2024)
- [PrismAvatar: Real-time animated 3D neural head avatars on edge devices](https://mlsanity.com/paper/2502.07030/) (2025)
- [Efficient Neural Light Fields (ENeLF) for Mobile Devices](https://mlsanity.com/paper/2406.00598/) (2024)
- [G-NeLF: Memory- and Data-Efficient Hybrid Neural Light Field for Novel View Synthesis](https://mlsanity.com/paper/2409.05617/) (2024)
- [LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field](https://mlsanity.com/paper/2409.18057/) (2024)
- [PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2605.10307/) (2026)

## Abstract (arXiv)

Real-time novel-view image synthesis on mobile devices is prohibitive due to the limited computational power and storage. Using volumetric rendering methods, such as NeRF and its derivatives, on mobile devices is not suitable due to the high computational cost of volumetric rendering. On the other hand, recent advances in neural light field representations have shown promising real-time view synthesis results on mobile devices. Neural light field methods learn a direct mapping from a ray representation to the pixel color. The current choice of ray representation is either stratified ray sampling or Plucker coordinates, overlooking the classic light slab (two-plane) representation, the preferred representation to interpolate between light field views. In this work, we find that using the light slab representation is an efficient representation for learning a neural light field. More importantly, it is a lower-dimensional ray representation enabling us to learn the 4D ray space using feature grids which are significantly faster to train and render. Although mostly designed for frontal views, we show that the light-slab representation can be further extended to non-frontal scenes using a divide-and-conquer strategy. Our method offers superior rendering quality compared to previous light field methods and achieves a significantly improved trade-off between rendering quality and speed.