Content-Aware Supervision For Diffusion-Based Restoration of Extremely Compressed Background For VCM

We propose content-aware supervision (CAS) techniques for diffusion-based restoration of an extremely compressed background for video coding for machines (VCM). First, we develop a CAS block to exploit prior information in an input image to reconstruct the noisy image, which is used as the input for the pretrained diffusion model. Then, we construct a refinement block to guide the pretrained diffusion model at each diffusion step by incorporating a degradation model and correction gradient estimation. Experimental results demonstrate the proposed algorithm outperforms state-of-the-art algorithms.