CharDiff: Improving Sampling Convergence via Characteristic Function Consistency in Diffusion Models

Abhishek Kumar Sinha, S. Manthira Moorthi; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 3955-3964

Abstract


Diffusion models have demonstrated extensive capabilities for generative modelling in both conditional and conditional image synthesis tasks. The reverse sampling has been the center of interest to improve the overall image quality without retraining the model from scratch. In this work we propose a plug-and-play module by utilizing the characteristic function of the distributions to minimize sampling drift. We experiment with existing diffusion solvers with our module in-place during denoising step to provide additional performance gain in image synthesis linear inverse problem tasks and text-conditioned image synthesis. Moreover We theoretically establish the effectiveness of the method in terms of improved Frechet Inception Distance (FID) and second order Tweedie moment for reduced trajectory deviation.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Sinha_2025_WACV, author = {Sinha, Abhishek Kumar and Moorthi, S. Manthira}, title = {CharDiff: Improving Sampling Convergence via Characteristic Function Consistency in Diffusion Models}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {3955-3964} }