High Resolution
High-resolution imaging and data processing are crucial for advancing numerous scientific fields, aiming to improve accuracy and detail in various applications. Current research focuses on developing and applying deep learning models, including diffusion models, transformers, and graph neural networks, to enhance resolution in diverse data types such as images, videos, and sensor readings. This work is significantly impacting fields ranging from weather forecasting and medical imaging to remote sensing and autonomous driving, enabling more precise analyses and improved decision-making. The development of high-resolution datasets and benchmark evaluations is also a key focus, facilitating the comparison and improvement of these advanced models.
Papers
AnomalyCD: A benchmark for Earth anomaly change detection with high-resolution and time-series observations
Jingtao Li, Qian Zhu, Xinyu Wang, Hengwei Zhao, Yanfei Zhong
DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
Wei Wu, Xi Guo, Weixuan Tang, Tingxuan Huang, Chiyu Wang, Dongyue Chen, Chenjing Ding
Unified Deep Learning Model for Global Prediction of Aboveground Biomass, Canopy Height and Cover from High-Resolution, Multi-Sensor Satellite Imagery
Manuel Weber, Carly Beneke, Clyde Wheeler
HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models
Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Deepu John, Bo Ji
HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
Runhui Huang, Xinpeng Ding, Chunwei Wang, Jianhua Han, Yulong Liu, Hengshuang Zhao, Hang Xu, Lu Hou, Wei Zhang, Xiaodan Liang
Adaptive Deep Iris Feature Extractor at Arbitrary Resolutions
Yuho Shoji, Yuka Ogino, Takahiro Toizumi, Atsushi Ito