One Size Fits All: Hypernetwork for Tunable Image Restoration
- URL: http://arxiv.org/abs/2206.05970v1
- Date: Mon, 13 Jun 2022 08:33:14 GMT
- Title: One Size Fits All: Hypernetwork for Tunable Image Restoration
- Authors: Shai Aharon and Gil Ben-Artzi
- Abstract summary: We introduce a novel approach for tunable image restoration that achieves the accuracy of multiple models, each optimized for a different level of degradation.
Our model can be optimized to restore as many degradation levels as required with a constant number of parameters and for various image restoration tasks.
- Score: 5.33024001730262
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: We introduce a novel approach for tunable image restoration that achieves the
accuracy of multiple models, each optimized for a different level of
degradation, with exactly the same number of parameters as a single model. Our
model can be optimized to restore as many degradation levels as required with a
constant number of parameters and for various image restoration tasks.
Experiments on real-world datasets show that our approach achieves state-of-the
art results in denoising, DeJPEG and super-resolution with respect to existing
tunable models, allowing smoother and more accurate fitting over a wider range
of degradation levels.
Related papers
- Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding [67.57487747508179]
Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model.
In this paper, we propose a novel multiple-in-one IR model that can effectively restore images with both single and mixed degradations.
arXiv Detail & Related papers (2024-11-25T09:26:34Z) - A Simple Approach to Unifying Diffusion-based Conditional Generation [63.389616350290595]
We introduce a simple, unified framework to handle diverse conditional generation tasks.
Our approach enables versatile capabilities via different inference-time sampling schemes.
Our model supports additional capabilities like non-spatially aligned and coarse conditioning.
arXiv Detail & Related papers (2024-10-15T09:41:43Z) - Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models [14.25759541950917]
This work leverages a capable vision-language model and a synthetic degradation pipeline to learn image restoration in the wild (wild IR)
Our base diffusion model is the image restoration SDE (IR-SDE)
arXiv Detail & Related papers (2024-04-15T12:34:21Z) - Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration [100.54419875604721]
All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation.
We propose DyNet, a dynamic family of networks designed in an encoder-decoder style for all-in-one image restoration tasks.
Our DyNet can seamlessly switch between its bulkier and lightweight variants, thereby offering flexibility for efficient model deployment.
arXiv Detail & Related papers (2024-04-02T17:58:49Z) - Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts [52.39959535724677]
We introduce an alternative solution to improve the generalization of image restoration models.
We propose AdaptIR, a Mixture-of-Experts (MoE) with multi-branch design to capture local, global, and channel representation bases.
Our AdaptIR achieves stable performance on single-degradation tasks, and excels in hybrid-degradation tasks, with fine-tuning only 0.6% parameters for 8 hours.
arXiv Detail & Related papers (2023-12-12T14:27:59Z) - Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and
Cycle Idempotence [76.93002743194974]
We propose a method to treat arbitrary rescaling, both upscaling and downscaling, as one unified process.
The proposed model is able to learn upscaling and downscaling simultaneously and achieve bidirectional arbitrary image rescaling.
It is shown to be robust in cycle idempotence test, free of severe degradations in reconstruction accuracy when the downscaling-to-upscaling cycle is applied repetitively.
arXiv Detail & Related papers (2022-03-02T07:42:15Z) - Perceptual Image Restoration with High-Quality Priori and Degradation
Learning [28.93489249639681]
We show that our model performs well in measuring the similarity between restored and degraded images.
Our simultaneous restoration and enhancement framework generalizes well to real-world complicated degradation types.
arXiv Detail & Related papers (2021-03-04T13:19:50Z) - 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) - Image Restoration from Parametric Transformations using Generative
Models [4.467248776406006]
We develop optimum techniques for various image restoration problems using generative models.
Our approach is capable of restoring images that are distorted by transformations even when the latter contain unknown parameters.
We extend our method to accommodate mixtures of multiple images where each image is described by its own generative model.
arXiv Detail & Related papers (2020-05-27T01:14:40Z)
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.