Conventional methods for scalable image coding for humans and machines require the transmission of additional information to achieve scalability. A recent diffusion-based method avoids this by generating human-oriented images from machine-oriented images without extra bitrate. This method, however, uses a single random seed, which may lead to suboptimal image quality. In this paper, we propose a seed selection method that identifies the optimal seed from multiple candidates to improve image quality without increasing the bitrate. To reduce computational cost, the selection is performed based on intermediate outputs obtained from early steps of the reverse diffusion process. Experimental results demonstrate that our method outperforms the baseline across multiple metrics.
View on arXiv