Jing Dong

Deep learning based face-swap videos, widely known as deepfakes, have drawn wide attention due to their threat to information credibility. Recent works mainly focus on the problem of deepfake detection that aims to reliably tell deepfakes apart from real ones, in an objective way. On the other hand, the subjective perception of deepfakes, especially its computational modeling, imitation, is also a significant problem but lacks adequate study. In this paper, we focus on the photorealism assessment of deepfakes, which is defined as the automatic assessment of deepfake photorealism that approximates human perception of deepfakes. It is important for evaluating the quality, deceptiveness of deepfakes which can be used for predicting the influence of deepfakes on Internet, it also has potentials in improving the deepfake generation process by serving as a critic. This paper promotes this new direction by presenting a comprehensive benchmark called DREAM, which stands for Deepfake photoREalism AssessMent. It is comprised of a deepfake video dataset of diverse quality, a large scale annotation that includes 140, 000 photorealism scores, textual descriptions obtained from 3, 500 human annotators, a comprehensive evaluation, analysis of 18 representative photorealism assessment methods, including recent large vision language model based methods, a newly proposed description-aligned CLIP method. The benchmark, insights included in this study can lay the foundation for future research in this direction, other related areas.

The rapid development of face forgery technology has raised concerns among researchers about information security. To mitigate the malicious abuse of the technology, deepfake detection has proven to be an effective countermeasure. However, existing methods only provide a true-false and binary classification, and they lack research on uncertainty estimation, which leads to the predictive reliability being unknown. The model uncertainty reflects its understanding of knowledge. Even when faced with unseen deepfake content, a detector without awareness of its cognitive limitations may still output incorrect predictions with high confidence. The detector assigns extremely high probabilities to samples, which is referred to a phenomenon known as overconfidence. In this paper, we introduce the novel concept of deepfake detection calibration, which focuses on aligning predicted probability with actual distribution to alleviate the overconfidence and estimate the uncertainty. Specifically, we introduce an innovative calibration method called packed-ensembles (PE), which divides a detector into multiple subnetworks. PE allows each subnetwork to focus on different forgery traces, resulting in reliable predictions without incurring additional computational costs. Comprehensive experiments demonstrate that our method effectively mitigates the overconfidence in deepfake detection while maintaining generalization, and significantly enhances detection reliability.

The rapid progress of multi-modal large language models (MLLMs) has boosted the task of image quality assessment (IQA). However, a key challenge arises from the inherent mismatch between the discrete token outputs of MLLMs and the continuous nature of quality scores required by IQA tasks. This discrepancy significantly hinders the performance of MLLM-based IQA methods. Previous approaches that convert discrete token predictions into continuous scores often suffer from conversion errors. Moreover, the semantic confusion introduced by level tokens (e.g., ``good'') further constrains the performance of MLLMs on IQA tasks and degrades their original capabilities for related tasks. To tackle these problems, we provide a theoretical analysis of the errors inherent in previous approaches and, motivated by this analysis, propose a simple yet effective framework, Q-Scorer. This framework incorporates a lightweight regression module and IQA-specific score tokens into the MLLM pipeline. Extensive experiments demonstrate that Q-Scorer achieves state-of-the-art performance across multiple IQA benchmarks, generalizes well to mixed datasets, and further improves when combined with other methods.

Although recent text-to-image (T2I) models have significantly improved the overall visual quality of generated images, they still struggle in the generation of accurate details in complex local regions, especially human hands. Generated hands often exhibit structural distortions and unrealistic textures, which can be very noticeable even when the rest of the body is well-generated. However, the quality assessment of hand regions remains largely neglected, limiting downstream task performance like human-centric generation quality optimization and AIGC detection. To address this, we propose the first quality assessment task targeting generated hand regions and showcase its abundant downstream applications. We first introduce the HandPair dataset for training hand quality assessment models. It consists of 48k images formed by high- and low-quality hand pairs, enabling low-cost, efficient supervision without manual annotation. Based on it, we develop HandEval, a carefully designed hand-specific quality assessment model. It leverages the powerful visual understanding capability of Multimodal Large Language Model (MLLM) and incorporates prior knowledge of hand keypoints, gaining strong perception of hand quality. We further construct a human-annotated test set with hand images from various state-of-the-art (SOTA) T2I models to validate its quality evaluation capability. Results show that HandEval aligns better with human judgments than existing SOTA methods. Furthermore, we integrate HandEval into image generation and AIGC detection pipelines, prominently enhancing generated hand realism and detection accuracy, respectively, confirming its universal effectiveness in downstream applications. Code and dataset will be available.