Liyuan Pan

Face images play a crucial role in numerous applications; however, real-world conditions frequently introduce degradations such as noise, blur, and compression artifacts, affecting overall image quality and hindering subsequent tasks. To address this challenge, we organized the VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops. Participants created lightweight and efficient models (limited to 0.5 GFLOPs and 5 million parameters) for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations. Submissions underwent comprehensive evaluations through correlation metrics on a dataset of in-the-wild face images. This challenge attracted 127 participants, with 1519 final submissions. This report summarizes the methodologies and findings for advancing the development of practical FIQA approaches.

Deep neural networks have achieved significant success in image dehazing. However, existing backbones face an irreconcilable trade-off between the global receptive field and computational efficiency, hindering further applications. State space models, such as Mamba, offer a potential solution to this conflict by modeling long-range dependencies with linear complexity. Although Mamba is well-suited for sequential tasks (e.g., natural language processing), it still encounters challenges when applied to low-level vision tasks. In this work, we propose a large multi-modal model (LMM) guided, Mamba-based image dehazing method (DehazeMamba). It enhances the standard Mamba architecture by incorporating image quality priors provided by the LMM and a channel attention mechanism. Additionally, we present a challenging image dehazing dataset and conduct new benchmark studies based on the LMM, evaluating hazy images and dehazing results by simulating human perception. Our experimental results demonstrate that our dataset exhibits superior haze quality, and our method outperforms current state-of-the-art (SOTA) dehazing methods by achieving a performance improvement of more than 5% on both the O-Haze and Dense-Haze datasets.