Lin Zhang, Bingqiu Chen, Fei Qin, Guangxing Li, Haibo Yuan, Yi Ren

Interstellar dust is a fundamental component of the Milky Way, influencing star formation, galactic evolution, and observations across the electromagnetic spectrum. Using red clump stars selected from near- and mid-infrared photometry, together with stellar catalogs from previous studies, we construct dust density maps of the Galactic plane ({$|Z|<25$}\,pc) covering the full $360^\circ$ in longitude and reaching distances up to $7$\,kpc. By applying a U-Net convolutional neural network to invert the line-of-sight extinction distribution, we obtain dust density maps at resolutions of $10$, $50$, and $100$\,pc, which reveal detailed structures including spiral arms, inter-arm spurs, and giant cavities. The dust distribution in the Galactic plane exhibits a morphology closely resembling that of the so-called Phantom galaxy M74. The derived exponential scale length of the Galactic dust disk is $2.90$\,kpc, slightly larger than that of the stellar thin disk. Our publicly available dust maps provide a new benchmark for extinction correction, studies of Galactic structure, and the investigation of the interplay between star formation and the interstellar medium.