UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis
- URL: http://arxiv.org/abs/2502.06324v1
- Date: Mon, 10 Feb 2025 10:20:11 GMT
- Title: UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis
- Authors: Zemin Yang, Yujing Sun, Xidong Peng, Siu Ming Yiu, Yuexin Ma,
- Abstract summary: Image demoir'eing poses one of the most formidable challenges in image restoration.
We propose a universal image demoir'eing solution, UniDemoir'e, which has superior generalization capability.
- Score: 17.930454451440944
- License:
- Abstract: Image demoir\'eing poses one of the most formidable challenges in image restoration, primarily due to the unpredictable and anisotropic nature of moir\'e patterns. Limited by the quantity and diversity of training data, current methods tend to overfit to a single moir\'e domain, resulting in performance degradation for new domains and restricting their robustness in real-world applications. In this paper, we propose a universal image demoir\'eing solution, UniDemoir\'e, which has superior generalization capability. Notably, we propose innovative and effective data generation and synthesis methods that can automatically provide vast high-quality moir\'e images to train a universal demoir\'eing model. Our extensive experiments demonstrate the cutting-edge performance and broad potential of our approach for generalized image demoir\'eing.
Related papers
- FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration [66.61201445650323]
Existing methods suffer from a generalization bottleneck in real-world scenarios.
We contribute a million-scale dataset with two notable advantages over existing training data.
We propose a robust model, FoundIR, to better address a broader range of restoration tasks in real-world scenarios.
arXiv Detail & Related papers (2024-12-02T12:08:40Z) - Beyond Pixels: Text Enhances Generalization in Real-World Image Restoration [47.942948541067544]
We propose using text as an auxiliary invariant representation to reactivate the generative capabilities of diffusion-based restoration models.
We introduce Res-Captioner, a module that generates enhanced textual descriptions tailored to image content and degradation levels.
We present RealIR, a new benchmark designed to capture diverse real-world scenarios.
arXiv Detail & Related papers (2024-12-01T16:36:22Z) - DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance [11.44012694656102]
Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains.
Existing large-scale diffusion models are confined to generating images of up to 1K resolution.
We propose a novel progressive approach that fully utilizes generated low-resolution images to guide the generation of higher-resolution images.
arXiv Detail & Related papers (2024-06-26T16:10:31Z) - FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis [48.9652334528436]
We introduce an innovative, training-free approach FouriScale from the perspective of frequency domain analysis.
We replace the original convolutional layers in pre-trained diffusion models by incorporating a dilation technique along with a low-pass operation.
Our method successfully balances the structural integrity and fidelity of generated images, achieving an astonishing capacity of arbitrary-size, high-resolution, and high-quality generation.
arXiv Detail & Related papers (2024-03-19T17:59:33Z) - Uni-Removal: A Semi-Supervised Framework for Simultaneously Addressing
Multiple Degradations in Real-World Images [6.3351090376024155]
Uni-Removal is a twostage semi-supervised framework for addressing the removal of multiple degradations in real-world images.
In the knowledge transfer stage, Uni-Removal leverages a supervised multi-teacher and student architecture.
In the domain adaptation stage, unsupervised fine-tuning is performed by incorporating an adversarial discriminator on real-world images.
arXiv Detail & Related papers (2023-07-11T07:18:15Z) - UMat: Uncertainty-Aware Single Image High Resolution Material Capture [2.416160525187799]
We propose a learning-based method to recover normals, specularity, and roughness from a single diffuse image of a material.
Our method is the first one to deal with the problem of modeling uncertainty in material digitization.
arXiv Detail & Related papers (2023-05-25T17:59:04Z) - GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from
Multi-view Images [79.39247661907397]
We introduce an effective framework Generalizable Model-based Neural Radiance Fields to synthesize free-viewpoint images.
Specifically, we propose a geometry-guided attention mechanism to register the appearance code from multi-view 2D images to a geometry proxy.
arXiv Detail & Related papers (2023-03-24T03:32:02Z) - Auto-regressive Image Synthesis with Integrated Quantization [55.51231796778219]
This paper presents a versatile framework for conditional image generation.
It incorporates the inductive bias of CNNs and powerful sequence modeling of auto-regression.
Our method achieves superior diverse image generation performance as compared with the state-of-the-art.
arXiv Detail & Related papers (2022-07-21T22:19:17Z) - A Generic Approach for Enhancing GANs by Regularized Latent Optimization [79.00740660219256]
We introduce a generic framework called em generative-model inference that is capable of enhancing pre-trained GANs effectively and seamlessly.
Our basic idea is to efficiently infer the optimal latent distribution for the given requirements using Wasserstein gradient flow techniques.
arXiv Detail & Related papers (2021-12-07T05:22:50Z)
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.