“In response to the problems of low feature matching accuracy, noise in predicted depth maps, and incomplete edge reconstruction in multi view stereo tasks of remote sensing images, the research team proposed a diffusion constrained multi view stereo network called DiffusionMVS. The feature enhancement module MFE-FPN, adaptive feature aggregation module AFA, and diffusion constrained optimization model DCM were designed, and the MAE index was improved by 28.11% and 3.37% on the WHU-TLC and LuoJia MVS datasets, respectively, demonstrating good reconstruction performance and generalization ability.”