GeoGuide: Geometric Guidance of Diffusion Models

Mateusz Poleski, Jacek Tabor, Przemyslaw Spurek; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 297-305

Diffusion models are currently one of the most effective tools in image generation. This is in particular due to the fact that contrary to GANs during training they can be easily conditioned. However given a pretrained diffusion guiding it to obtain desired result is typically a more delicate task. A typical technique based on the probabilistic derivation lies in adding the rescaled gradient of the classifier during backward propagation. In this paper we switch the perspective from probabilistic to metric. By studying the distance of the trajectory of the diffusion model from the data manifold we introduce a new guideance model GeoGuide. GeoGuide is not only easy to apply as it is based on classifier gradient normalization but it outperforms the probabilistic approach both with respect to FID and the quality of generated images.