# Neural Lens Modeling

arXiv: https://arxiv.org/abs/2304.04848 · HTML: https://mlsanity.com/paper/2304.04848/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 10 Apr 2023.

## Builds on (most cited first, 21 of 21)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Invertible Residual Networks](https://mlsanity.com/paper/1811.00995/) (2018)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [NeRF--: Neural Radiance Fields Without Known Camera Parameters](https://mlsanity.com/paper/2102.07064/) (2021)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve](https://mlsanity.com/paper/1912.02908/) (2019)
- [UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images](https://mlsanity.com/paper/1908.07070/) (2019)
- [Deep ChArUco: Dark ChArUco Marker Pose Estimation](https://mlsanity.com/paper/1812.03247/) (2018)
- [BabelCalib: A Universal Approach to Calibrating Central Cameras](https://mlsanity.com/paper/2109.09704/) (2021)
- [E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markers](https://mlsanity.com/paper/2105.14184/) (2021)
- [Learnable Visual Markers](https://mlsanity.com/paper/1610.09237/) (2016)
- [Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping](https://mlsanity.com/paper/2209.15165/) (2022)
- [DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers](https://mlsanity.com/paper/2206.08026/) (2022)

## Built on by (most cited first, 7 of 7)

- [Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras](https://mlsanity.com/paper/2409.04751/) (2024)
- [Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction](https://mlsanity.com/paper/2502.09563/) (2025)
- [PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction](https://mlsanity.com/paper/2601.18336/) (2026)
- [Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges](https://mlsanity.com/paper/2402.12041/) (2024)
- [PRaDA: Projective Radial Distortion Averaging](https://mlsanity.com/paper/2504.16499/) (2025)
- [SurgCalib: Gaussian Splatting-Based Hand-Eye Calibration for Robot-Assisted Minimally Invasive Surgery](https://mlsanity.com/paper/2603.08983/) (2026)
- [DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization](https://mlsanity.com/paper/2604.00648/) (2026)

## Abstract (arXiv)

Recent methods for 3D reconstruction and rendering increasingly benefit from end-to-end optimization of the entire image formation process. However, this approach is currently limited: effects of the optical hardware stack and in particular lenses are hard to model in a unified way. This limits the quality that can be achieved for camera calibration and the fidelity of the results of 3D reconstruction. In this paper, we propose NeuroLens, a neural lens model for distortion and vignetting that can be used for point projection and ray casting and can be optimized through both operations. This means that it can (optionally) be used to perform pre-capture calibration using classical calibration targets, and can later be used to perform calibration or refinement during 3D reconstruction, e.g., while optimizing a radiance field. To evaluate the performance of our proposed model, we create a comprehensive dataset assembled from the Lensfun database with a multitude of lenses. Using this and other real-world datasets, we show that the quality of our proposed lens model outperforms standard packages as well as recent approaches while being much easier to use and extend. The model generalizes across many lens types and is trivial to integrate into existing 3D reconstruction and rendering systems.