EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding

ArXi:2603.18001v1 Announce Type: new In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with accurate layouts and high fidelity to text descriptions (e.g., spatial relationships), while grounding the image robustly at the same time. We believe that image grounding possesses strong text and layout understanding abilities, which can compensate for the corresponding limitations in layout-to-image generation.