HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

TL;DR

HAODiff is a novel human-aware diffusion model that effectively restores human-centered images degraded by noise and motion blur using dual-prompt guidance, outperforming existing methods.

Contribution

The paper introduces a triple-branch dual-prompt guidance mechanism and a synthetic degradation pipeline for robust one-step image restoration.

Findings

HAODiff outperforms state-of-the-art methods in quantitative metrics.

The dual-prompt guidance enhances robustness against diverse degradations.

The MPII-Test benchmark effectively evaluates combined noise and motion blur restoration.

Abstract

Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems often coexist in practice. To address this, we design a degradation pipeline that simulates the coexistence of HMB and generic noise, generating synthetic degraded data to train our proposed HAODiff, a human-aware one-step diffusion. Specifically, we propose a triple-branch dual-prompt guidance (DPG), which leverages high-quality images, residual noise (LQ minus HQ), and HMB segmentation masks as training targets. It produces a positive-negative prompt pair for classifier-free guidance (CFG) in a single diffusion step. The resulting adaptive dual prompts let HAODiff exploit CFG more effectively, boosting robustness against diverse degradations. For fair evaluation, we introduce MPII-Test, a benchmark rich in combined noise and HMB cases. Extensive experiments show that our HAODiff surpasses existing state-of-the-art (SOTA) methods in terms of both quantitative metrics and visual quality on synthetic and real-world datasets, including our introduced MPII-Test. Code is available at: https://github.com/gobunu/HAODiff.