TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
This work addresses the computational expense of diffusion models for image super-resolution, enabling practical deployment with reduced model size and inference cost.
TOC-SR proposes a framework to build efficient one-step super-resolution models by discovering a compact diffusion backbone, achieving a 6.6x reduction in parameters and 2.8x reduction in GMACs while maintaining reconstruction quality.
Diffusion models have recently demonstrated strong performance for image restoration tasks, including super-resolution. However, their large model size and iterative sampling procedures make them computationally expensive for practical deployment. In this work, we present TOC-SR, a framework for building efficient one-step super-resolution models by first discovering a compact diffusion backbone. Starting from a sixteen-channel latent diffusion model, we construct parameter-efficient surrogate blocks using feature-wise generative distillation and perform architecture discovery using epsilon-constrained Bayesian Optimization to minimize model complexity while preserving generative fidelity. The resulting compact diffusion backbone achieves a 6.6x reduction in parameters and a 2.8x reduction in GMACs compared to the expanded diffusion model. We then adapt this backbone for super-resolution and distill the diffusion process into a single-step generator. Experiments demonstrate that the proposed approach enables efficient super-resolution while maintaining strong reconstruction quality.