DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914173021061120 |
|---|---|
| author | Peng, Siran Zhang, Haoyuan Gao, Li Zhang, Tianshuo Zhu, Xiangyu Li, Bao Zhao, Weisong Lei, Zhen |
| author_facet | Peng, Siran Zhang, Haoyuan Gao, Li Zhang, Tianshuo Zhu, Xiangyu Li, Bao Zhao, Weisong Lei, Zhen |
| contents | The rapid evolution of deepfake technologies demands robust and reliable face forgery detection algorithms. While determining whether an image has been manipulated remains essential, the ability to precisely localize forgery clues is also important for enhancing model explainability and building user trust. To address this dual challenge, we introduce DiffusionFF, a diffusion-based framework that simultaneously performs face forgery detection and fine-grained artifact localization. Our key idea is to establish a novel encoder-decoder architecture: a pretrained forgery detector serves as a powerful "artifact encoder", and a denoising diffusion model is repurposed as an "artifact decoder". Conditioned on multi-scale forgery-related features extracted by the encoder, the decoder progressively synthesizes a detailed artifact localization map. We then fuse this fine-grained localization map with high-level semantic features from the forgery detector, leading to substantial improvements in detection capability. Extensive experiments show that DiffusionFF achieves state-of-the-art (SOTA) performance across multiple benchmarks, underscoring its superior effectiveness and explainability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization Peng, Siran Zhang, Haoyuan Gao, Li Zhang, Tianshuo Zhu, Xiangyu Li, Bao Zhao, Weisong Lei, Zhen Computer Vision and Pattern Recognition The rapid evolution of deepfake technologies demands robust and reliable face forgery detection algorithms. While determining whether an image has been manipulated remains essential, the ability to precisely localize forgery clues is also important for enhancing model explainability and building user trust. To address this dual challenge, we introduce DiffusionFF, a diffusion-based framework that simultaneously performs face forgery detection and fine-grained artifact localization. Our key idea is to establish a novel encoder-decoder architecture: a pretrained forgery detector serves as a powerful "artifact encoder", and a denoising diffusion model is repurposed as an "artifact decoder". Conditioned on multi-scale forgery-related features extracted by the encoder, the decoder progressively synthesizes a detailed artifact localization map. We then fuse this fine-grained localization map with high-level semantic features from the forgery detector, leading to substantial improvements in detection capability. Extensive experiments show that DiffusionFF achieves state-of-the-art (SOTA) performance across multiple benchmarks, underscoring its superior effectiveness and explainability. |
| title | DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01873 |