2 papers
cs.CV2026
Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning
Yang Deng, David Mould, Paul L. Rosin +1
Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized bypr…
cs.CV2025
By-Example Synthesis of Vector Textures
Christopher Palazzolo, Oliver van Kaick, David Mould
We propose a new method for synthesizing an arbitrarily sized novel vector texture given a single raster exemplar. Our method first segments the exemplar to extract the primary tex…