Skip to main content

🏢 University of Virginia

Learning 3D Representations from Procedural 3D Programs
·4094 words·20 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision 3D Vision 🏢 University of Virginia
Self-supervised learning of 3D representations from procedurally generated synthetic shapes achieves comparable performance to models trained on real-world datasets, highlighting the potential of synt…