Physics-Driven Turbulence Image Restoration with Stochastic Refinement
- URL: http://arxiv.org/abs/2307.10603v1
- Date: Thu, 20 Jul 2023 05:49:21 GMT
- Title: Physics-Driven Turbulence Image Restoration with Stochastic Refinement
- Authors: Ajay Jaiswal, Xingguang Zhang, Stanley H. Chan, Zhangyang Wang
- Abstract summary: Image distortion by atmospheric turbulence is a critical problem in long-range optical imaging systems.
Fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions.
This paper proposes the Physics-integrated Restoration Network (PiRN) to help the network to disentangle theity from the degradation and the underlying image.
- Score: 80.79900297089176
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Image distortion by atmospheric turbulence is a stochastic degradation, which
is a critical problem in long-range optical imaging systems. A number of
research has been conducted during the past decades, including model-based and
emerging deep-learning solutions with the help of synthetic data. Although fast
and physics-grounded simulation tools have been introduced to help the
deep-learning models adapt to real-world turbulence conditions recently, the
training of such models only relies on the synthetic data and ground truth
pairs. This paper proposes the Physics-integrated Restoration Network (PiRN) to
bring the physics-based simulator directly into the training process to help
the network to disentangle the stochasticity from the degradation and the
underlying image. Furthermore, to overcome the ``average effect" introduced by
deterministic models and the domain gap between the synthetic and real-world
degradation, we further introduce PiRN with Stochastic Refinement (PiRN-SR) to
boost its perceptual quality. Overall, our PiRN and PiRN-SR improve the
generalization to real-world unknown turbulence conditions and provide a
state-of-the-art restoration in both pixel-wise accuracy and perceptual
quality. Our codes are available at \url{https://github.com/VITA-Group/PiRN}.
Related papers
- 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) - Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance.
Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs.
In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
arXiv Detail & Related papers (2023-11-20T08:27:56Z) - Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A
New Physics-Inspired Transformer Model [82.23276183684001]
We propose a physics-inspired transformer model for imaging through atmospheric turbulence.
The proposed network utilizes the power of transformer blocks to jointly extract a dynamical turbulence distortion map.
We present two new real-world turbulence datasets that allow for evaluation with both classical objective metrics and a new task-driven metric using text recognition accuracy.
arXiv Detail & Related papers (2022-07-20T17:09:16Z) - Physics to the Rescue: Deep Non-line-of-sight Reconstruction for
High-speed Imaging [13.271762773872476]
We present a novel deep model that incorporates the complementary physics priors of wave propagation and volume rendering into a neural network for high-quality and robust NLOS reconstruction.
Our method outperforms prior physics and learning based approaches on both synthetic and real measurements.
arXiv Detail & Related papers (2022-05-03T02:47:02Z) - A comparison of different atmospheric turbulence simulation methods for
image restoration [64.24948495708337]
Atmospheric turbulence deteriorates the quality of images captured by long-range imaging systems.
Various deep learning-based atmospheric turbulence mitigation methods have been proposed in the literature.
We systematically evaluate the effectiveness of various turbulence simulation methods on image restoration.
arXiv Detail & Related papers (2022-04-19T16:21:36Z) - Frequency-Aware Physics-Inspired Degradation Model for Real-World Image
Super-Resolution [18.328806055594576]
We formulate a real-world physics-inspired degradationmodel by considering bothoptics andsensordegradation.
We propose to use a convolutional neural network (CNN) to learn the cutoff frequency of real-world degradation process.
We evaluatethe effectiveness and generalization capability of the proposed degradation model on real-world images captured by different imaging systems.
arXiv Detail & Related papers (2021-11-05T07:30:00Z) - Learning to Restore a Single Face Image Degraded by Atmospheric
Turbulence using CNNs [93.72048616001064]
Images captured under such condition suffer from a combination of geometric deformation and space varying blur.
We present a deep learning-based solution to the problem of restoring a turbulence-degraded face image.
arXiv Detail & Related papers (2020-07-16T15:25:08Z) - Turbulence Enrichment using Physics-informed Generative Adversarial
Networks [0.0]
We develop methods for generative enrichment of turbulence.
We incorporate a physics-informed learning approach by a modification to the loss function.
We show that using the physics-informed learning can also significantly improve the model's ability in generating data that satisfies the physical governing equations.
arXiv Detail & Related papers (2020-03-04T06:14:11Z)
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.