ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts
This addresses the challenge of generating diverse and consistent images from text prompts for applications in computer vision and graphics, though it appears incremental by building on existing shape guidance techniques.
The paper tackles the problem of text-to-image synthesis by incorporating 3D shape guidance to generate images that are more text-compliant and aesthetically plausible, with results showing improved consistency and shape awareness compared to conventional methods.
We introduce ShapeWords, an approach for synthesizing images based on 3D shape guidance and text prompts. ShapeWords incorporates target 3D shape information within specialized tokens embedded together with the input text, effectively blending 3D shape awareness with textual context to guide the image synthesis process. Unlike conventional shape guidance methods that rely on depth maps restricted to fixed viewpoints and often overlook full 3D structure or textual context, ShapeWords generates diverse yet consistent images that reflect both the target shape's geometry and the textual description. Experimental results show that ShapeWords produces images that are more text-compliant, aesthetically plausible, while also maintaining 3D shape awareness.