# Neural Light Spheres for Implicit Image Stitching and View Synthesis

arXiv: https://arxiv.org/abs/2409.17924 · HTML: https://mlsanity.com/paper/2409.17924/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 68 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [DeepStereo: Learning to Predict New Views from the World's Imagery](https://mlsanity.com/paper/1506.06825/) (2015)
- [Layered Neural Atlases for Consistent Video Editing](https://mlsanity.com/paper/2109.11418/) (2021)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray](https://mlsanity.com/paper/2202.01020/) (2022)
- [MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images](https://mlsanity.com/paper/2008.06534/) (2020)
- [Learning Neural Light Fields with Ray-Space Embedding Networks](https://mlsanity.com/paper/2112.01523/) (2021)
- [Neural Surface Maps](https://mlsanity.com/paper/2103.16942/) (2021)
- [Deep Multi Depth Panoramas for View Synthesis](https://mlsanity.com/paper/2008.01815/) (2020)
- [Neural Image Representations for Multi-Image Fusion and Layer Separation](https://mlsanity.com/paper/2108.01199/) (2021)
- [Neural Spline Fields for Burst Image Fusion and Layer Separation](https://mlsanity.com/paper/2312.14235/) (2023)
- [Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography](https://mlsanity.com/paper/2212.12324/) (2022)

## Built on by (most cited first, 6 of 6)

- [Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment](https://mlsanity.com/paper/2504.01503/) (2025)
- [AIM 2025 Low-light RAW Video Denoising Challenge: Dataset, Methods and Results](https://mlsanity.com/paper/2508.16830/) (2025)
- [Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis](https://mlsanity.com/paper/2602.18322/) (2026)
- [Light 'em Up: Enabling Few-Shot Low-Light 3D Gaussian Splatting with Multi-Scale Explicit Retinex Illumination Decoupling](https://mlsanity.com/paper/2604.24053/) (2026)
- [Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis](https://mlsanity.com/paper/2607.01663/) (2026)
- [PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction](https://mlsanity.com/paper/2609.06099/) (2026)

## Abstract (arXiv)

Challenging to capture, and challenging to display on a cellphone screen, the panorama paradoxically remains both a staple and underused feature of modern mobile camera applications. In this work we address both of these challenges with a spherical neural light field model for implicit panoramic image stitching and re-rendering; able to accommodate for depth parallax, view-dependent lighting, and local scene motion and color changes during capture. Fit during test-time to an arbitrary path panoramic video capture -- vertical, horizontal, random-walk -- these neural light spheres jointly estimate the camera path and a high-resolution scene reconstruction to produce novel wide field-of-view projections of the environment. Our single-layer model avoids expensive volumetric sampling, and decomposes the scene into compact view-dependent ray offset and color components, with a total model size of 80 MB per scene, and real-time (50 FPS) rendering at 1080p resolution. We demonstrate improved reconstruction quality over traditional image stitching and radiance field methods, with significantly higher tolerance to scene motion and non-ideal capture settings.