Towards Seamless Lunar Mosaics: Deep Radiometric Normalization for Cross-Sensor Orbital Imagery Using Chandrayaan-2 TMC Data
Researchers have developed a deep learning framework to address radiometric inconsistencies in lunar mosaics created from different orbital imagery sources. The system utilizes a conditional generative adversarial network (cGAN) to map conventionally mosaicked images to a photometrically consistent reference. This approach, tested with Chandrayaan-2 TMC and SELENE data, significantly improves tonal uniformity and reduces seam artifacts compared to traditional methods. AI
IMPACT Enhances the fidelity of planetary surface maps by improving image mosaicking techniques.