Neural Lens Modeling

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.

[1]  Clayton D. Scott,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Rafał K. Mantiuk,et al.  Distilling Style from Image Pairs for Global Forward and Inverse Tone Mapping , 2022, CVMP.

[3]  M. Pollefeys,et al.  Camera Pose Estimation using Implicit Distortion Models , 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  T. Müller,et al.  Instant neural graphics primitives with a multiresolution hash encoding , 2022, ACM Trans. Graph..

[5]  M. Stamminger,et al.  ADOP , 2021, ACM Trans. Graph..

[6]  Christopher Zach,et al.  BabelCalib: A Universal Approach to Calibrating Central Cameras , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Minsu Cho,et al.  Self-Calibrating Neural Radiance Fields , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Min H. Kim,et al.  DeepFormableTag , 2021, ACM Trans. Graph..

[9]  Yanfeng Liu,et al.  E2ETag: An End-to-End Trainable Method for Generating and Detecting Fiducial Markers , 2021, BMVC.

[10]  Tom Gedeon,et al.  Invertible Denoising Network: A Light Solution for Real Noise Removal , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Antonio Torralba,et al.  BARF: Bundle-Adjusting Neural Radiance Fields , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  S. Fidler,et al.  Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  V. Prisacariu,et al.  NeRF-: Neural Radiance Fields Without Known Camera Parameters , 2021, ArXiv.

[14]  Ivan Kobyzev,et al.  Normalizing Flows: An Introduction and Review of Current Methods , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Pratul P. Srinivasan,et al.  NeRF , 2020, ECCV.

[16]  Torsten Sattler,et al.  Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Wan-Yen Lo,et al.  Accelerating 3D deep learning with PyTorch3D , 2019, SIGGRAPH Asia 2020 Courses.

[18]  Matthew Fisher,et al.  UprightNet: Geometry-Aware Camera Orientation Estimation From Single Images , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Felix Heide,et al.  Hyperparameter optimization in black-box image processing using differentiable proxies , 2019, ACM Trans. Graph..

[20]  Quoc V. Le,et al.  Searching for MobileNetV3 , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[21]  Titus Cieslewski,et al.  Are We Ready for Autonomous Drone Racing? The UZH-FPV Drone Racing Dataset , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[22]  Jean Charles Bazin,et al.  DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view cameras , 2018, CVMP '18.

[23]  Tomasz Malisiewicz,et al.  Deep ChArUco: Dark ChArUco Marker Pose Estimation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Jens Behrmann,et al.  Invertible Residual Networks , 2018, ICML.

[25]  Rafael Muñoz-Salinas,et al.  Speeded up detection of squared fiducial markers , 2018, Image Vis. Comput..

[26]  Stephen P. Boyd,et al.  End-to-end optimization of optics and image processing for achromatic extended depth of field and super-resolution imaging , 2018, ACM Trans. Graph..

[27]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[28]  David Duvenaud,et al.  Neural Ordinary Differential Equations , 2018, NeurIPS.

[29]  Andrea Torsello,et al.  Parameter-Free Lens Distortion Calibration of Central Cameras , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[30]  Srikumar Ramalingam,et al.  A Unifying Model for Camera Calibration , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Pascal Monasse,et al.  A Precision Analysis of Camera Distortion Models , 2017, IEEE Trans. Image Process..

[32]  Victor S. Lempitsky,et al.  Learnable Visual Markers , 2016, NIPS.

[33]  Francisco José Madrid-Cuevas,et al.  Generation of fiducial marker dictionaries using Mixed Integer Linear Programming , 2016, Pattern Recognit..

[34]  Torsten Sattler,et al.  Non-parametric Structure-Based Calibration of Radially Symmetric Cameras , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[35]  Kari Pulli,et al.  FlexISP , 2014, ACM Trans. Graph..

[36]  Yoshua Bengio,et al.  NICE: Non-linear Independent Components Estimation , 2014, ICLR.

[37]  Marc Pollefeys,et al.  A multiple-camera system calibration toolbox using a feature descriptor-based calibration pattern , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[38]  Edwin Olson,et al.  AprilTag: A robust and flexible visual fiducial system , 2011, 2011 IEEE International Conference on Robotics and Automation.

[39]  Marc Pollefeys,et al.  Robust Radiometric Calibration and Vignetting Correction , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  Ralf Reulke,et al.  Determination and improvement of spatial resolution of the CCD-line-scanner system ADS40 , 2006 .

[41]  Roland Siegwart,et al.  A Flexible Technique for Accurate Omnidirectional Camera Calibration and Structure from Motion , 2006, Fourth IEEE International Conference on Computer Vision Systems (ICVS'06).

[42]  Sing Bing Kang,et al.  Parameter-Free Radial Distortion Correction with Center of Distortion Estimation , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Etienne Grossmann,et al.  Non-parametric self-calibration , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[44]  Andrew W. Fitzgibbon,et al.  A rational function lens distortion model for general cameras , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[45]  Peter F. Sturm,et al.  Towards complete generic camera calibration , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[46]  Peter F. Sturm,et al.  A Generic Concept for Camera Calibration , 2004, ECCV.

[47]  Shree K. Nayar,et al.  A perspective on distortions , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[48]  Andrew W. Fitzgibbon,et al.  Simultaneous linear estimation of multiple view geometry and lens distortion , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[49]  O. Faugeras,et al.  Straight lines have to be straight , 2001, Machine Vision and Applications.

[50]  Shree K. Nayar,et al.  A general imaging model and a method for finding its parameters , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[51]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[52]  Jitendra Malik,et al.  Recovering high dynamic range radiance maps from photographs , 1997, SIGGRAPH '08.

[53]  Einari Kilpelä,et al.  Compensation of systematic errors of image and model coordinates , 1981 .

[54]  Serge J. Belongie,et al.  Geometry Processing with Neural Fields , 2023, NeurIPS.

[55]  Leonidas J. Guibas,et al.  ShapeFlow: Learnable Deformation Flows Among 3D Shapes , 2020, NeurIPS.

[56]  Aubrey K. Dunne,et al.  Efficient Generic Calibration Method for General Cameras with Single Centre of Projection , 2007, IEEE International Conference on Computer Vision.

[57]  Duane C. Brown,et al.  Close-Range Camera Calibration , 1971 .