SOURCE-LINKED INTELLIGENCE

PrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Professional photo finishing relies on both global adjustments and region-specific local edits guided by semantic masks, yet current automated methods handle this workflow only partially. We present PrismGPT, a Vision-Language Model (VLM) framework that produces structured, region-aware editing plans from a single input image without relying on commercial black-box tools. Training a VLM to simultaneously diagnose aesthetic deficiencies at both global and local levels while predicting precise editing parameters is challenging due to the vast combinatorial decision space. We address this through

Read original source ↗ Open in workspace

recordType

paper

region

Global