This repository is the code implementation of the paper STT: Building Extraction from Remote Sensing Images with Sparse Token Transformers. This branch has been tested with PyTorch 2.x and CUDA 12.1, ...

The semantic parsing of building facade images is a fundamental yet challenging task in urban scene understanding. Existing works sought to tackle this task by using facade grammars or convolutional ...

Multimedia communication is becoming pervasive because of the progress in wireless communications and multimedia coding. Estimating the quality of the visual content accurately is crucial in providing ...