Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning
An RL framework that fine-tunes image layer decomposition models using VLM-as-judge rewards, eliminating paired supervision.
ciara-rowles
Ciara Rowles
•
•
1 min read
Collaborative Control for Geometry-Conditioned PBR Image Generation
Current 3D content generation builds on generative models that output RGB images. Modern graphics pipelines, however, require physically-based rendering (PBR) material properties. …
shimon-vainer