3 papers
cs.CV2026
SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination
Athanasios Tragakis, Marco Aversa, Daniela Ivanova +4
SceneHI is a framework that lifts high-resolution, illumination-aware priors from 2D diffusion models to perform 3D texture synthesis. It is the first to demonstrate that high-reso…
cs.CV2025
Autoguided Online Data Curation for Diffusion Model Training
Valeria Pais, Luis Oala, Daniele Faccio +1
The costs of generative model compute rekindled promises and hopes for efficient data curation. In this work, we investigate whether recently developed autoguidance and online data…
cs.CV2024
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models
Athanasios Tragakis, Marco Aversa, Chaitanya Kaul +2
In this work, we introduce Pixelsmith, a zero-shot text-to-image generative framework to sample images at higher resolutions with a single GPU. We are the first to show that it is…