A Natural Language Guided Approach for Blind Face Restoration: Methodology and Dataset

Blind Face Restoration (BFR) aims to reconstruct high-quality face images from low-quality inputs without any prior knowledge of degradation types or levels. Recent advances, particularly through GAN- and diffusion-based approaches, have greatly improved perceptual realism and reconstruction fidelity. However, existing approaches typically rely solely on visual cues from degraded images. This often results in inaccurate reconstruction of facial details and noticeable identity distortion, particularly under severe or complex degradations. To address these limitations, we incorporate auxiliary textual information into BFR to facilitate the recovery of subtle facial attributes, such as wrinkles and moles, which are often overlooked by conventional visual priors. To support this idea, we first construct a large-scale dataset containing 30,000 detailed textual descriptions paired with CelebA-HQ images to capture fine-grained facial semantics. To bridge the gap between visual data and natural language, we further propose FaceCLIP, a fine-tuned vision-language model specifically tailored to human faces, enabling more accurate image-text alignment by capturing nuanced semantic cues critical for faithful reconstruction. Built upon these foundations, we propose Text-guided Blind Face Restoration (TBFR), a diffusion-based framework that explicitly integrates textual guidance into the restoration process. Within TBFR, a text-guided hybrid attention block fuses visual and textual features, and a text-aware loss enforces semantic consistency. Extensive experiments demonstrate that TBFR outperforms state-of-the-art BFR methods in both quantitative metrics and perceptual quality, establishing a new benchmark for BFR tasks.