Towards Robust and Generalizable Lensless Imaging with Modular Learned Reconstruction
- URL: http://arxiv.org/abs/2502.01102v1
- Date: Mon, 03 Feb 2025 06:46:39 GMT
- Title: Towards Robust and Generalizable Lensless Imaging with Modular Learned Reconstruction
- Authors: Eric Bezzam, Yohann Perron, Martin Vetterli,
- Abstract summary: State-of-the-art lensless imaging techniques combine physical modeling and neural networks.
Generalizability of learned approaches to lensless measurements of new masks has not been studied.
We use a modular learned reconstruction in which a key component is a pre-processor prior to image recovery.
- Score: 7.368155086339779
- License:
- Abstract: Lensless cameras disregard the conventional design that imaging should mimic the human eye. This is done by replacing the lens with a thin mask, and moving image formation to the digital post-processing. State-of-the-art lensless imaging techniques use learned approaches that combine physical modeling and neural networks. However, these approaches make simplifying modeling assumptions for ease of calibration and computation. Moreover, the generalizability of learned approaches to lensless measurements of new masks has not been studied. To this end, we utilize a modular learned reconstruction in which a key component is a pre-processor prior to image recovery. We theoretically demonstrate the pre-processor's necessity for standard image recovery techniques (Wiener filtering and iterative algorithms), and through extensive experiments show its effectiveness for multiple lensless imaging approaches and across datasets of different mask types (amplitude and phase). We also perform the first generalization benchmark across mask types to evaluate how well reconstructions trained with one system generalize to others. Our modular reconstruction enables us to use pre-trained components and transfer learning on new systems to cut down weeks of tedious measurements and training. As part of our work, we open-source four datasets, and software for measuring datasets and for training our modular reconstruction.
Related papers
- Enhancing Low-dose CT Image Reconstruction by Integrating Supervised and
Unsupervised Learning [13.17680480211064]
We propose a hybrid supervised-unsupervised learning framework for X-ray computed tomography (CT) image reconstruction.
Each proposed trained block consists of a deterministic MBIR solver and a neural network.
We demonstrate the efficacy of this learned hybrid model for low-dose CT image reconstruction with limited training data.
arXiv Detail & Related papers (2023-11-19T20:23:59Z) - Disruptive Autoencoders: Leveraging Low-level features for 3D Medical
Image Pre-training [51.16994853817024]
This work focuses on designing an effective pre-training framework for 3D radiology images.
We introduce Disruptive Autoencoders, a pre-training framework that attempts to reconstruct the original image from disruptions created by a combination of local masking and low-level perturbations.
The proposed pre-training framework is tested across multiple downstream tasks and achieves state-of-the-art performance.
arXiv Detail & Related papers (2023-07-31T17:59:42Z) - Not All Image Regions Matter: Masked Vector Quantization for
Autoregressive Image Generation [78.13793505707952]
Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook.
We propose a novel two-stage framework, which consists of Masked Quantization VAE (MQ-VAE) Stack model from modeling redundancy.
arXiv Detail & Related papers (2023-05-23T02:15:53Z) - PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling [83.67628239775878]
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT.
This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction.
We propose a remarkably simple and effective method, ourmethod, that entails two strategies.
arXiv Detail & Related papers (2023-03-04T13:38:51Z) - The Devil is in the Frequency: Geminated Gestalt Autoencoder for
Self-Supervised Visual Pre-Training [13.087987450384036]
We present a new Masked Image Modeling (MIM), termed Geminated Autoencoder (Ge$2$-AE) for visual pre-training.
Specifically, we equip our model with geminated decoders in charge of reconstructing image contents from both pixel and frequency space.
arXiv Detail & Related papers (2022-04-18T09:22:55Z) - Unrolled Primal-Dual Networks for Lensless Cameras [0.45880283710344055]
We show that learning a supervised primal-dual reconstruction method results in image quality matching state of the art in the literature.
This improvement stems from our finding that embedding learnable forward and adjoint models in a learned primal-dual optimization framework can even improve the quality of reconstructed images.
arXiv Detail & Related papers (2022-03-08T19:21:39Z) - Is Deep Image Prior in Need of a Good Education? [57.3399060347311]
Deep image prior was introduced as an effective prior for image reconstruction.
Despite its impressive reconstructive properties, the approach is slow when compared to learned or traditional reconstruction techniques.
We develop a two-stage learning paradigm to address the computational challenge.
arXiv Detail & Related papers (2021-11-23T15:08:26Z) - Model-based Reconstruction with Learning: From Unsupervised to
Supervised and Beyond [8.847248042144681]
We briefly discuss classical model-based reconstruction methods and then review reconstruction methods at the intersection of model-based and learning-based paradigms in detail.
This review includes many recent methods based on unsupervised learning, and supervised learning, as well as a framework to combine multiple types of learned models together.
arXiv Detail & Related papers (2021-03-26T15:33:59Z) - SIR: Self-supervised Image Rectification via Seeing the Same Scene from
Multiple Different Lenses [82.56853587380168]
We propose a novel self-supervised image rectification (SIR) method based on an important insight that the rectified results of distorted images of the same scene from different lens should be the same.
We leverage a differentiable warping module to generate the rectified images and re-distorted images from the distortion parameters.
Our method achieves comparable or even better performance than the supervised baseline method and representative state-of-the-art methods.
arXiv Detail & Related papers (2020-11-30T08:23:25Z) - FlatNet: Towards Photorealistic Scene Reconstruction from Lensless
Measurements [31.353395064815892]
We propose a non-iterative deep learning based reconstruction approach that results in orders of magnitude improvement in image quality for lensless reconstructions.
Our approach, called $textitFlatNet$, lays down a framework for reconstructing high-quality photorealistic images from mask-based lensless cameras.
arXiv Detail & Related papers (2020-10-29T09:20:22Z) - NAS-DIP: Learning Deep Image Prior with Neural Architecture Search [65.79109790446257]
Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior.
We propose to search for neural architectures that capture stronger image priors.
We search for an improved network by leveraging an existing neural architecture search algorithm.
arXiv Detail & Related papers (2020-08-26T17:59:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.