AI Paper Atlas

Research map / Detection and segmentation / CNN features

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization

Siran Peng, Haoyuan Zhang, Li Gao, Tianshuo Zhang, Xiangyu Zhu, Bao Li, Weisong Zhao, Zhen Lei

CVPR 2026 · Detection and segmentation › CNN features · approach: Forgery detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DiffusionFF to EfficientNet-B4 detectorEfficientNet-B4 · DFDC (cross-dataset)AUC (%): 72.42 -> 82.19Improved
add DiffusionFF to ConvNeXt-B detectorConvNeXt-B · CDF2 (cross-dataset)AUC (%): 96.08 -> 97.24Improved
add DiffusionFF to Swin-B detectorSwin-B · DFDC (cross-dataset)AUC (%): 82.81 -> 84.54Improved
use diffusion instead of direct regression for DSSIM estimation (ablation)DiffusionFF · FF++ DSSIM estimationFID: 172.213 -> 43.093Improved
run diffusion at pixel level instead of latent space (ablation)DiffusionFF · FF++ DSSIM estimationFID: 56.384 -> 43.093Improved
multi-stage conditioning instead of final-stage only (ablation)DiffusionFF · FF++ DSSIM estimationFID: 43.812 -> 43.093Improved
encoder-based conditioning instead of decoder conditioning (ablation)DiffusionFF · FF++ DSSIM estimationFID: 46.329 -> 43.093Improved
gating fusion instead of addition (ablation)DiffusionFF · Cross-dataset average AUCAUC (%): 90.10 -> 90.85Improved
gating fusion instead of cross-attention (ablation)DiffusionFF · Cross-dataset average AUCAUC (%): 90.71 -> 90.85Improved
DiffusionFF vs existing DSSIM regression methods for map qualityLiSiam / LRL · CDF2 DSSIM estimationFID: 256.201 -> 98.982Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy