Texture and Noise Dual Adaptation for Infrared Image Super-Resolution
- URL: http://arxiv.org/abs/2311.08816v2
- Date: Thu, 20 Feb 2025 08:51:25 GMT
- Title: Texture and Noise Dual Adaptation for Infrared Image Super-Resolution
- Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Yafei Dong, Shinichiro Omachi,
- Abstract summary: Target-oriented Domain Adaptation SRGAN (DASRGAN) is an innovative framework for robust IR super-resolution model adaptation.<n>DASRGAN operates on the synergy of two key components: 1) Texture-Oriented Adaptation (TOA) to refine texture details meticulously, and 2) Noise-Oriented Adaptation (NOA) to minimize noise transfer.
- Score: 7.310003050012592
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent efforts have explored leveraging visible light images to enrich texture details in infrared (IR) super-resolution. However, this direct adaptation approach often becomes a double-edged sword, as it improves texture at the cost of introducing noise and blurring artifacts. To address these challenges, we propose the Target-oriented Domain Adaptation SRGAN (DASRGAN), an innovative framework specifically engineered for robust IR super-resolution model adaptation. DASRGAN operates on the synergy of two key components: 1) Texture-Oriented Adaptation (TOA) to refine texture details meticulously, and 2) Noise-Oriented Adaptation (NOA), dedicated to minimizing noise transfer. Specifically, TOA uniquely integrates a specialized discriminator, incorporating a prior extraction branch, and employs a Sobel-guided adversarial loss to align texture distributions effectively. Concurrently, NOA utilizes a noise adversarial loss to distinctly separate the generative and Gaussian noise pattern distributions during adversarial training. Our extensive experiments confirm DASRGAN's superiority. Comparative analyses against leading methods across multiple benchmarks and upsampling factors reveal that DASRGAN sets new state-of-the-art performance standards. Code are available at \url{https://github.com/yongsongH/DASRGAN}.
Related papers
- RetinexDual: Retinex-based Dual Nature Approach for Generalized Ultra-High-Definition Image Restoration [5.075864600930347]
RetinexDual is a novel Retinex theory-based framework designed for generalized Ultra-High-Definition Image Restoration (UHD IR) tasks.<n>We evaluate RetinexDual on four UHD IR tasks, namely deraining, deblurring, dehazing, and Low-Light Image Enhancement (LLIE)
arXiv Detail & Related papers (2025-08-06T18:15:05Z) - NOFT: Test-Time Noise Finetune via Information Bottleneck for Highly Correlated Asset Creation [70.96827354717459]
diffusion model has provided a strong tool for implementing text-to-image (T2I) and image-to-image (I2I) generation.<n>We propose a noise finetune NOFT module employed by Stable Diffusion to generate highly correlated and diverse images.
arXiv Detail & Related papers (2025-05-18T05:09:47Z) - LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis [17.470869402542533]
Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs.
We propose LL-Gaussian, a novel framework for 3D reconstruction and enhancement from low-light sRGB images.
Compared to state-of-the-art NeRF-based methods, LL-Gaussian achieves up to 2,000 times faster inference and reduces training time to just 2%.
arXiv Detail & Related papers (2025-04-14T15:39:31Z) - FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion [63.87313550399871]
Image-event joint depth estimation methods leverage complementary modalities for robust perception, yet face challenges in generalizability.
We propose Self-supervised Transfer (PST) and FrequencyDe-coupled Fusion module (FreDF)
PST establishes cross-modal knowledge transfer through latent space alignment with image foundation models.
FreDF explicitly decouples high-frequency edge features from low-frequency structural components, resolving modality-specific frequency mismatches.
arXiv Detail & Related papers (2025-03-25T15:04:53Z) - LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object Detection [18.804394986840887]
LEGNet is a lightweight network that incorporates a novel edge-Gaussian aggregation module for low-quality remote sensing images.
Our key innovation lies in the synergistic integration of Scharr operator-based edge priors with uncertainty-aware Gaussian modeling.
LEGNet achieves state-of-the-art performance across five benchmark datasets while ensuring computational efficiency.
arXiv Detail & Related papers (2025-03-18T08:20:24Z) - The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation [31.599902235859687]
We propose to leverage an aligned Gaussian noise as implicit guidance to complement explicit user-defined inputs, such as text prompts.
NoiseQuery enables fine-grained control and yields significant performance boosts over high-level semantics and over low-level visual attributes.
arXiv Detail & Related papers (2024-12-06T14:59:00Z) - Few-shot NeRF by Adaptive Rendering Loss Regularization [78.50710219013301]
Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF)
Recent works demonstrate that the frequency regularization of Positional rendering can achieve promising results for few-shot NeRF.
We propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF.
arXiv Detail & Related papers (2024-10-23T13:05:26Z) - Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement [71.13353154514418]
Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge.
We present a novel Mamba scanning mechanism, called RAWMamba, to effectively handle raw images with different CFAs.
We also present a Retinex Decomposition Module (RDM) grounded in Retinex prior, which decouples illumination from reflectance to facilitate more effective denoising and automatic non-linear exposure correction.
arXiv Detail & Related papers (2024-09-11T06:12:03Z) - Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective [45.210030086193775]
Current synthetic image detection (SID) pipelines are primarily dedicated to crafting universal artifact features.
We propose SAFE, a lightweight and effective detector with three simple image transformations.
Our pipeline achieves a new state-of-the-art performance, with remarkable improvements of 4.5% in accuracy and 2.9% in average precision against existing methods.
arXiv Detail & Related papers (2024-08-13T09:01:12Z) - Frequency Domain Modality-invariant Feature Learning for
Visible-infrared Person Re-Identification [79.9402521412239]
We propose a novel Frequency Domain modality-invariant feature learning framework (FDMNet) to reduce modality discrepancy from the frequency domain perspective.
Our framework introduces two novel modules, namely the Instance-Adaptive Amplitude Filter (IAF) and the Phrase-Preserving Normalization (PPNorm)
arXiv Detail & Related papers (2024-01-03T17:11:27Z) - Learn From Orientation Prior for Radiograph Super-Resolution:
Orientation Operator Transformer [8.009052363001903]
High-resolution radiographic images play a pivotal role in the early diagnosis and treatment of skeletal muscle-related diseases.
It is promising to enhance image quality by introducing single-image super-resolution (SISR) model into the radiology image field.
The conventional image pipeline, which can learn a mixed mapping between SR and denoising from the color space and inter-pixel patterns, poses a particular challenge for radiographic images with limited pattern features.
arXiv Detail & Related papers (2023-12-27T07:56:24Z) - Rethinking the Up-Sampling Operations in CNN-based Generative Network
for Generalizable Deepfake Detection [86.97062579515833]
We introduce the concept of Neighboring Pixel Relationships(NPR) as a means to capture and characterize the generalized structural artifacts stemming from up-sampling operations.
A comprehensive analysis is conducted on an open-world dataset, comprising samples generated by tft28 distinct generative models.
This analysis culminates in the establishment of a novel state-of-the-art performance, showcasing a remarkable tft11.6% improvement over existing methods.
arXiv Detail & Related papers (2023-12-16T14:27:06Z) - Learning to See Low-Light Images via Feature Domain Adaptation [17.033219611079165]
We propose a single-stage network empowered by Feature Domain Adaptation (FDA) to decouple the denoising and color mapping tasks in raw LLIE.
FDA can explore the global and local correlations with fewer line buffers.
Our method achieves state-of-the-art performance with fewer computing costs.
arXiv Detail & Related papers (2023-12-11T03:38:26Z) - Adaptive Sparse Convolutional Networks with Global Context Enhancement
for Faster Object Detection on Drone Images [26.51970603200391]
This paper investigates optimizing the detection head based on the sparse convolution.
It suffers from inadequate integration of contextual information of tiny objects.
We propose a novel global context-enhanced adaptive sparse convolutional network.
arXiv Detail & Related papers (2023-03-25T14:42:50Z) - Hierarchical Similarity Learning for Aliasing Suppression Image
Super-Resolution [64.15915577164894]
A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing.
HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
arXiv Detail & Related papers (2022-06-07T14:55:32Z) - Aggregated Contextual Transformations for High-Resolution Image
Inpainting [57.241749273816374]
We propose an enhanced GAN-based model, named Aggregated COntextual-Transformation GAN (AOT-GAN) for high-resolution image inpainting.
To enhance context reasoning, we construct the generator of AOT-GAN by stacking multiple layers of a proposed AOT block.
For improving texture synthesis, we enhance the discriminator of AOT-GAN by training it with a tailored mask-prediction task.
arXiv Detail & Related papers (2021-04-03T15:50:17Z) - SFANet: A Spectrum-aware Feature Augmentation Network for
Visible-Infrared Person Re-Identification [12.566284647658053]
We propose a novel spectrum-aware feature augementation network named SFANet for cross-modality matching problem.
Learning with grayscale-spectrum images, our model can apparently reduce modality discrepancy and detect inner structure relations.
In feature-level, we improve the conventional two-stream network through balancing the number of specific and sharable convolutional blocks.
arXiv Detail & Related papers (2021-02-24T08:57:32Z) - Image Fine-grained Inpainting [89.17316318927621]
We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields.
To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss.
We also employ a discriminator with local and global branches to ensure local-global contents consistency.
arXiv Detail & Related papers (2020-02-07T03:45:25Z)
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.