Hugging Peers

VectorSynth

☆ Save
by MVRL image-to-image diffusers apache-2.0
48 downloads 0 likes on Hugging Face updated

Papers using or citing this model 1

  • VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics 5 citations · 2025 · IEEE Workshop/Winter Conference on Applications of Computer Vision · arXiv

    We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth...