High Resolution Image
High-resolution image processing focuses on developing methods to effectively acquire, process, and analyze images with significantly increased detail, aiming to improve accuracy and efficiency in various applications. Current research emphasizes overcoming computational limitations of existing deep learning models (like CNNs and Transformers) when handling high-resolution inputs, focusing on novel architectures such as state-space models and diffusion models to enhance efficiency and quality. These advancements are crucial for fields like medical imaging, microscopy, and remote sensing, where high-resolution data is essential for accurate diagnosis, analysis, and decision-making. The development of efficient algorithms for high-resolution image processing is driving progress across numerous scientific disciplines and practical applications.
Papers
TransResNet: Integrating the Strengths of ViTs and CNNs for High Resolution Medical Image Segmentation via Feature Grafting
Muhammad Hamza Sharif, Dmitry Demidov, Asif Hanif, Mohammad Yaqub, Min Xu
Leveraging generative models to characterize the failure conditions of image classifiers
Adrien LeCoz, Stéphane Herbin, Faouzi Adjed
ESOD: Efficient Small Object Detection on High-Resolution Images
Kai Liu, Zhihang Fu, Sheng Jin, Ze Chen, Fan Zhou, Rongxin Jiang, Yaowu Chen, Jieping Ye
INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model
Yiwei Ma, Zhibin Wang, Xiaoshuai Sun, Weihuang Lin, Qiang Zhou, Jiayi Ji, Rongrong Ji