- 1Cheng Kar-Shun Robotics Institute, The Hong Kong University of Science and Technology, Hong Kong
- 2EMIA, AIS, The Hong Kong University of Science and Technology, Hong Kong
- 3Department of Physics, The Hong Kong University of Science and Technology, Hong Kong
- 4MAE, The Hong Kong University of Science and Technology, Hong Kong
- 5Space Science Center, Insitute for advanced Study, Shenzhen University, Shenzhen, China
Due to the limitations of communication bandwidth, the transmission of high-resolution images or videos between spacecrafts such as satellites and planetary landers and ground stations has always been a challenging task. To address the issue of high-resolution image transmission, we propose a novel image transmission paradigm based on reference-based super resolution (Ref-SR). This approach involves the simultaneous transmission of both high-resolution and low-resolution images between the spacecraft and ground stations. The low-resolution images are transmitted at a high frame rate, while the high-resolution images are transmitted at a lower frame rate. The high-resolution images serve as references to enhance the quality of the low-resolution images, thereby optimizing bandwidth usage while maintaining image clarity. Compared to directly applying super resolution to low-resolution images, which introducing image distortion due to the domain bias between the space image and its training images, our proposed method keeps the consistency of the super-resolved images and the ground truth images. By using high-resolution images as references, the super resolution process is guided to produce more accurate and reliable high-resolution images. Previous ground-based experiments have demonstrated the feasibility of Ref-SR in image and video restoration, and we believe this method has great potential for lunar communication scenarios.
How to cite: Meng, G., Yang, S., Lu, J., Li, Y., and Cao, Y.: A Novel Image Transmission Paradigm for Lunar-to-Earth Communications with Reference-Based Super Resolution, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-17508, https://doi.org/10.5194/egusphere-egu25-17508, 2025.