Universal and Flexible Optical Aberration Correction Using Deep-Prior
Based Deconvolution
- URL: http://arxiv.org/abs/2104.03078v1
- Date: Wed, 7 Apr 2021 12:00:38 GMT
- Title: Universal and Flexible Optical Aberration Correction Using Deep-Prior
Based Deconvolution
- Authors: Xiu Li, Jinli Suo, Weihang Zhang, Xin Yuan, Qionghai Dai
- Abstract summary: We propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors.
Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters.
- Score: 51.274657266928315
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: High quality imaging usually requires bulky and expensive lenses to
compensate geometric and chromatic aberrations. This poses high constraints on
the optical hash or low cost applications. Although one can utilize algorithmic
reconstruction to remove the artifacts of low-end lenses, the degeneration from
optical aberrations is spatially varying and the computation has to trade off
efficiency for performance. For example, we need to conduct patch-wise
optimization or train a large set of local deep neural networks to achieve high
reconstruction performance across the whole image. In this paper, we propose a
PSF aware plug-and-play deep network, which takes the aberrant image and PSF
map as input and produces the latent high quality version via incorporating
lens-specific deep priors, thus leading to a universal and flexible optical
aberration correction method. Specifically, we pre-train a base model from a
set of diverse lenses and then adapt it to a given lens by quickly refining the
parameters, which largely alleviates the time and memory consumption of model
learning. The approach is of high efficiency in both training and testing
stages. Extensive results verify the promising applications of our proposed
approach for compact low-end cameras.
Related papers
- A Physics-Informed Blur Learning Framework for Imaging Systems [20.105957982007283]
We propose a physics-informed PSF learning framework for imaging systems.
Our framework could achieve both high accuracy and universal applicability.
Our approach demonstrates improvements in image quality in simulation and also showcases noticeable visual quality improvements on real captured images.
arXiv Detail & Related papers (2025-02-17T02:54:14Z) - Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction [30.529707438964596]
We present a self-calibrating framework that jointly optimize camera parameters, lens distortion and 3D Gaussian representations.
Our technique enables high-quality scene reconstruction from Large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images.
arXiv Detail & Related papers (2025-02-13T18:15:10Z) - Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem [23.833099288826045]
Training Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores.
However, they often results in blurry images due to insufficient recovery of high-frequency details.
We propose a novel method that incorporates Multi-Objective Optimization (MOO) into the training process of SISR models to balance perceptual quality and distortion.
arXiv Detail & Related papers (2024-09-05T02:14:04Z) - Towards Physics-informed Cyclic Adversarial Multi-PSF Lensless Imaging [0.5371337604556311]
We introduce a novel approach to multi-PSF lensless imaging, employing a dual discriminator cyclic adversarial framework.
We propose a unique generator architecture with a sparse convolutional PSF-aware auxiliary branch, coupled with a forward model integrated into the training loop.
Our method achieves comparable performance to existing PSF-agnostic generative methods for single PSF cases and demonstrates resilience to PSF changes without the need for retraining.
arXiv Detail & Related papers (2024-07-09T10:07:28Z) - DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image
Enhancement [77.0360085530701]
Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments.
Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features.
Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
arXiv Detail & Related papers (2023-12-12T06:07:21Z) - Improving Lens Flare Removal with General Purpose Pipeline and Multiple
Light Sources Recovery [69.71080926778413]
flare artifacts can affect image visual quality and downstream computer vision tasks.
Current methods do not consider automatic exposure and tone mapping in image signal processing pipeline.
We propose a solution to improve the performance of lens flare removal by revisiting the ISP and design a more reliable light sources recovery strategy.
arXiv Detail & Related papers (2023-08-31T04:58:17Z) - Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions.
The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result.
To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
arXiv Detail & Related papers (2023-08-10T07:53:06Z) - Neural Lens Modeling [50.57409162437732]
NeuroLens is a neural lens model for distortion and vignetting that can be used for point projection and ray casting.
It can be used to perform pre-capture calibration using classical calibration targets, and can later be used to perform calibration or refinement during 3D reconstruction.
The model generalizes across many lens types and is trivial to integrate into existing 3D reconstruction and rendering systems.
arXiv Detail & Related papers (2023-04-10T20:09:17Z) - Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly.
A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work.
It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
arXiv Detail & Related papers (2022-09-26T22:22:30Z)
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.