English

Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier

Computer Vision and Pattern Recognition 2026-03-24 v1

Abstract

In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distributional mismatches between the output of upstream models and the expected input of downstream models frequently degrade overall generation quality. To address this issue, we propose Uni-Classifier (Uni-C), a simple yet effective plug-and-play module that leverages video diffusion priors to guide the denoising process of preceding models, thereby aligning their outputs with downstream requirements. Uni-C can also be applied independently to enhance the output quality of individual generative models. Extensive experiments across video and 3D generation tasks demonstrate that Uni-C consistently improves generation quality in both workflow-based and standalone settings, highlighting its versatility and strong generalization capability.

Keywords

Cite

@article{arxiv.2603.20382,
  title  = {Uni-Classifier: Leveraging Video Diffusion Priors for Universal Guidance Classifier},
  author = {Yujie Zhou and Pengyang Ling and Jiazi Bu and Bingjie Gao and Li Niu},
  journal= {arXiv preprint arXiv:2603.20382},
  year   = {2026}
}

Comments

Accepted by ICME 2026

R2 v1 2026-07-01T11:30:31.268Z