High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer
M Li, H Sun, Y Lei, X Zhang, Y Dong, Y Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
Document images are often degraded by various stains, significantly impacting their
readability and hindering downstream applications such as document digitization and …
readability and hindering downstream applications such as document digitization and …
Beyond Model Adaptation at Test Time: A Survey
Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …
use cases and applications, under the prevailing assumption that training and test samples …
Test-Time Intensity Consistency Adaptation for Shadow Detection
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is
challenged by the diverse appearances of shadows caused by variations in illumination …
challenged by the diverse appearances of shadows caused by variations in illumination …
Uwformer: Underwater image enhancement via a semi-supervised multi-scale transformer
Underwater images often exhibit poor quality, distorted color balance and low contrast due
to the complex and intricate interplay of light, water, and objects. Despite the significant …
to the complex and intricate interplay of light, water, and objects. Despite the significant …
ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training
Social media is increasingly plagued by realistic fake images, making it hard to trust content.
Previous algorithms to detect these fakes often fail in new, real-world scenarios because …
Previous algorithms to detect these fakes often fail in new, real-world scenarios because …
Improving Unsupervised Video Object Segmentation via Fake Flow Generation
Unsupervised video object segmentation (VOS), also known as video salient object
detection, aims to detect the most prominent object in a video at the pixel level. Recently, two …
detection, aims to detect the most prominent object in a video at the pixel level. Recently, two …
Order-aware Interactive Segmentation
Interactive segmentation aims to accurately segment target objects with minimal user
interactions. However, current methods often fail to accurately separate target objects from …
interactions. However, current methods often fail to accurately separate target objects from …
Medical Visual Prompting (MVP): A Unified Framework for Versatile and High-Quality Medical Image Segmentation
Y Chen, G Huang, K Huang, Z Lin, G Zhong… - arXiv preprint arXiv …, 2024 - arxiv.org
Accurate segmentation of lesion regions is crucial for clinical diagnosis and treatment across
various diseases. While deep convolutional networks have achieved satisfactory results in …
various diseases. While deep convolutional networks have achieved satisfactory results in …
TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation
R Zhang, G Huang, Y Huo, X Yuan, Z Zhou… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative Adversarial Networks (GANs) have emerged as a prominent research focus for
image editing tasks, leveraging the powerful image generation capabilities of the GAN …
image editing tasks, leveraging the powerful image generation capabilities of the GAN …
Adaptive Query Prompting for Multi-Domain Landmark Detection
Medical landmark detection is crucial in various medical imaging modalities and
procedures. Although deep learning-based methods have achieve promising performance …
procedures. Although deep learning-based methods have achieve promising performance …