Curved Diffusion: A Generative Model With Optical Geometry Control
This addresses a specific need in computer vision for generating images with controlled optical effects, but it is incremental as it builds on existing diffusion models.
The paper tackles the problem of controlling camera geometry in image generation by integrating a text-to-image diffusion model with lens geometry, enabling manipulation of curvature properties like fish-eye and panoramic views.
State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image capture. The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a text-to-image diffusion model with the particular lens geometry used in image rendering. Our method is based on a per-pixel coordinate conditioning method, enabling the control over the rendering geometry. Notably, we demonstrate the manipulation of curvature properties, achieving diverse visual effects, such as fish-eye, panoramic views, and spherical texturing using a single diffusion model.