Residual Multiplicative Filter Networks for Multiscale Reconstruction

Coordinate networks like Multiplicative Filter Networks (MFNs) and BACON offer some control over the frequency spectrum used to represent continuous signals such as images or 3D volumes. Yet, they are not readily applicable to problems for which coarse-to-fine estimation is required, including various inverse problems in which coarse-to-fine optimization plays a key role in avoiding poor local minima. We introduce a new coordinate network architecture and training scheme that enables coarse-to-fine optimization with fine-grained control over the frequency support of learned reconstructions. This is achieved with two key innovations. First, we incorporate skip connections so that structure at one scale is preserved when fitting finer-scale structure. Second, we propose a novel initialization scheme to provide control over the model frequency spectrum at each stage of optimization. We demonstrate how these modifications enable multiscale optimization for coarse-to-fine fitting to natural images. We then evaluate our model on synthetically generated datasets for the the problem of single-particle cryo-EM reconstruction. We learn high resolution multiscale structures, on par with the state-of-the art.

[1]  Julien N. P. Martel,et al.  CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images , 2022, ECCV.

[2]  Jeong Joon Park,et al.  StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Xin Tong,et al.  GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Shalini De Mello,et al.  Efficient Geometry-aware 3D Generative Adversarial Networks , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  David B. Lindell,et al.  Bacon: Band-limited Coordinate Networks for Multiscale Scene Representation , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Adam K. Lerer,et al.  CryoDRGN2: Ab initio neural reconstruction of 3D protein structures from real cryo-EM images , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  D. Ratner,et al.  CryoPoseNet: End-to-End Simultaneous Learning of Single-particle Orientation and 3D Map Reconstruction from Cryo-electron Microscopy Data , 2021, 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).

[8]  C. Theobalt,et al.  NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction , 2021, NeurIPS.

[9]  O. Sorkine-Hornung,et al.  Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields , 2021, ICLR.

[10]  Gordon Wetzstein,et al.  Acorn , 2021, ACM Trans. Graph..

[11]  Hyojin Kim,et al.  Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  David J. Fleet,et al.  3D Flexible Refinement: Structure and Motion of Flexible Proteins from Cryo-EM , 2021, bioRxiv.

[13]  Andreas Geiger,et al.  UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[14]  R. Giryes,et al.  SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization , 2021, NeurIPS.

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

[16]  Yiyi Liao,et al.  KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[17]  Ren Ng,et al.  PlenOctrees for Real-time Rendering of Neural Radiance Fields , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[18]  Pratul P. Srinivasan,et al.  Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[19]  Gordon Wetzstein,et al.  Neural Lumigraph Rendering , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Brendt Wohlberg,et al.  CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems , 2021, 2102.05181.

[21]  Charles T. Loop,et al.  Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Ellen D. Zhong,et al.  CryoDRGN: Reconstruction of heterogeneous cryo-EM structures using neural networks , 2021, Nature Methods.

[23]  Jonathan T. Barron,et al.  iNeRF: Inverting Neural Radiance Fields for Pose Estimation , 2020, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Gordon Wetzstein,et al.  AutoInt: Automatic Integration for Fast Neural Volume Rendering , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Angjoo Kanazawa,et al.  pixelNeRF: Neural Radiance Fields from One or Few Images , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jiajun Wu,et al.  pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Francesc Moreno-Noguer,et al.  D-NeRF: Neural Radiance Fields for Dynamic Scenes , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  L. Tong,et al.  Cryo-EM as a powerful tool for drug discovery , 2020, Bioorganic & Medicinal Chemistry Letters.

[29]  Kyaw Zaw Lin,et al.  Neural Sparse Voxel Fields , 2020, NeurIPS.

[30]  Jonathan T. Barron,et al.  Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains , 2020, NeurIPS.

[31]  Gordon Wetzstein,et al.  Implicit Neural Representations with Periodic Activation Functions , 2020, NeurIPS.

[32]  Richard A. Newcombe,et al.  Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction , 2020, ECCV.

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

[34]  Thomas Funkhouser,et al.  Local Implicit Grid Representations for 3D Scenes , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Marc Pollefeys,et al.  Convolutional Occupancy Networks , 2020, ECCV.

[36]  Andreas Geiger,et al.  Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  David J. Fleet,et al.  Non-uniform refinement: adaptive regularization improves single-particle cryo-EM reconstruction , 2019, Nature Methods.

[38]  Thomas Funkhouser,et al.  Local Deep Implicit Functions for 3D Shape , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[40]  Hao Li,et al.  PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[41]  Thomas A. Funkhouser,et al.  Learning Shape Templates With Structured Implicit Functions , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[42]  Richard A. Newcombe,et al.  DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Sebastian Nowozin,et al.  Occupancy Networks: Learning 3D Reconstruction in Function Space , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Conrad C. Huang,et al.  UCSF ChimeraX: Meeting modern challenges in visualization and analysis , 2018, Protein science : a publication of the Protein Society.

[45]  David J. Fleet,et al.  cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination , 2017, Nature Methods.

[46]  Leslie Greengard,et al.  Rapid Solution of the Cryo-EM Reconstruction Problem by Frequency Marching , 2016, SIAM J. Imaging Sci..

[47]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[49]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[50]  W. Kühlbrandt The Resolution Revolution , 2014, Science.

[51]  Sjors H.W. Scheres,et al.  RELION: Implementation of a Bayesian approach to cryo-EM structure determination , 2012, Journal of structural biology.

[52]  M. van Heel,et al.  Fourier shell correlation threshold criteria. , 2005, Journal of structural biology.

[53]  N. Grigorieff,et al.  Accurate determination of local defocus and specimen tilt in electron microscopy. , 2003, Journal of structural biology.

[54]  Pawel A Penczek,et al.  Three-dimensional spectral signal-to-noise ratio for a class of reconstruction algorithms. , 2002, Journal of structural biology.

[55]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[56]  Martin Vetterli,et al.  Wavelets and filter banks: theory and design , 1992, IEEE Trans. Signal Process..

[57]  O. Rioul,et al.  Wavelets and signal processing , 1991, IEEE Signal Processing Magazine.

[58]  Edward H. Adelson,et al.  PYRAMID METHODS IN IMAGE PROCESSING. , 1984 .

[59]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[60]  Anit Kumar Sahu,et al.  Multiplicative Filter Networks , 2021, ICLR.

[61]  E. Kirkland Theory of Calculation of Images of Thick Specimens , 2020, Advanced Computing in Electron Microscopy.

[62]  Hamilton-Jacobi Equations,et al.  Multigrid Methods for , 2011 .

[63]  Wen Jiang,et al.  EMAN2: an extensible image processing suite for electron microscopy. , 2007, Journal of structural biology.

[64]  S. Mallat A wavelet tour of signal processing , 1998 .