visual-changenet Model by NVIDIA

nvidia/visual-changenetPREVIEW

Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask

image segmentation nvidia nim tao toolkit computer vision cv image image generation video vlm

API Reference

Input

This demo identifies pixel level changes in two images, reference and test, taken at different point in time. It uses the VisualChangeNet model trained on land satellite imagery dataset to identify changes in land over time. This is a semantic segmentation model that identifies 10 different types of changes in landscape.

Reference Image*

image.png

jpg, jpeg, png

Test Image*

image.png

jpg, jpeg, png

Output

Legend

Farmland to desert

Building to desert

Water to desert

Farmland to building

Desert to building

Desert to farmland

Building to farmland

Water to farmland

Desert to water