Boosting Flow-based Generative Super-Resolution Models via Learned Prior

Autor:	Tsao, Li-Yuan, Lo, Yi-Chen, Chang, Chia-Che, Chen, Hao-Wei, Tseng, Roy, Feng, Chien, Lee, Chun-Yi
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images. However, these methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature. To overcome these issues, this work introduces a conditional learned prior to the inference phase of a flow-based SR model. This prior is a latent code predicted by our proposed latent module conditioned on the low-resolution image, which is then transformed by the flow model into an SR image. Our framework is designed to seamlessly integrate with any contemporary flow-based SR model without modifying its architecture or pre-trained weights. We evaluate the effectiveness of our proposed framework through extensive experiments and ablation analyses. The proposed framework successfully addresses all the inherent issues in flow-based SR models and enhances their performance in various SR scenarios. Our code is available at: https://github.com/liyuantsao/BFSR Comment: Accepted to CVPR2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.10988 Zobrazit plný text záznamu View this record from Arxiv