Seed Selection for Human-Oriented Image Reconstruction via Guided Diffusion
This work addresses image quality issues in scalable image coding for humans and machines, but it is incremental as it builds on an existing diffusion-based approach.
The paper tackles the problem of suboptimal image quality in diffusion-based human-oriented image reconstruction by proposing a seed selection method that identifies optimal seeds from multiple candidates without increasing bitrate, and experimental results show it outperforms the baseline across multiple metrics.
Conventional methods for scalable image coding for humans and machines require the transmission of additional information to achieve scalability. A recent diffusion-based approach avoids this by generating human-oriented images from machine-oriented images without extra bitrate. However, it utilizes 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 the computational cost, selection is performed based on intermediate outputs obtained from early steps of the reverse diffusion process. Experimental results demonstrate that our proposed method outperforms the baseline, which uses a single random seed without selection, across multiple evaluation metrics.