Reproduce “Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yaoyi Qi, Xingxing Weng, Chao Pang, Yongkang Cui, Xiangyu Hao, Xiaokang Zhang, Guibo Zhu, Gui-Song Xia

KnowChange generates paired satellite images and pixel-level change labels by using a vision-language model to propose change locations and land-cover transitions from a pre-change image and requested task; generative models then produce post-change maps and imagery. In synthetic-only building change transfer, Know-BCD averages 39.71 IoU across four benchmarks versus 33.07 for Changen2-S1; it loses on LEVIR-CD.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.