FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
Not on the map. Why?
Abstract (arXiv)
With recent advances in computer vision and graphics, it is now possible to generate videos with extremely realistic synthetic faces, even in real time. Countless applications are possible, some of which raise a legitimate alarm, calling for reliable detectors of fake videos. In fact, distinguishing between original and manipulated video can be a challenge for humans and computers alike, especially when the videos are compressed or have low resolution, as it often happens on social networks. Research on the detection of face manipulations has been seriously hampered by the lack of adequate datasets. To this end, we introduce a novel face manipulation dataset of about half a million edited images (from over 1000 videos). The manipulations have been generated with a state-of-the-art face editing approach. It exceeds all existing video manipulation datasets by at least an order of magnitude. Using our new dataset, we introduce benchmarks for classical image forensic tasks, including classification and segmentation, considering videos compressed at various quality levels. In addition, we introduce a benchmark evaluation for creating indistinguishable forgeries with known ground truth; for instance with generative refinement models.
Key facts. Cited by 118 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Mar 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 22; 2022: 21; 2023: 25; 2024: 25; 2025: 14; 2026: 11.
118 papers.
Sort:
By area:
- 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
- 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
- 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
- 2021Neural Head Avatars from Monocular RGB Videoscited by 212
- 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 180
- 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
- 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
- 2022Generating Long Videos of Dynamic Scenescited by 113
- 2021Representative Forgery Mining for Fake Face Detectioncited by 108
- 2021One Shot Face Swapping on Megapixelscited by 105
- 2023CelebV-Text: A Large-Scale Facial Text-Video Datasetcited by 103
- 2023Emotional Speech-Driven Animation with Content-Emotion Disentanglementcited by 98
38 more
- 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
- 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
- 2021Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowdscited by 58
- 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
- 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusioncited by 53
- 2023Multimodal Automated Fact-Checking: A Surveycited by 51
- 2022Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videoscited by 50
- 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
- 2023HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Facescited by 48
- 2024Improved Video VAE for Latent Video Diffusion Modelcited by 46
- 2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
- 2023Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videoscited by 44
- 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
- 2021FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learningcited by 43
- 2023DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatarscited by 42
- 2023LEO: Generative Latent Image Animator for Human Video Synthesiscited by 40
- 2023MoStGAN-V: Video Generation with Temporal Motion Stylescited by 37
- 2023Evading DeepFake Detectors via Adversarial Statistical Consistencycited by 37
- 2021Live Speech Portraits: Real-Time Photorealistic Talking-Head Animationcited by 36
- 2024Dyadic Interaction Modeling for Social Behavior Generationcited by 32
- 2022Finding Directions in GAN's Latent Space for Neural Face Reenactmentcited by 27
- 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
- 2024Matten: Video Generation with Mamba-Attentioncited by 24
- 2024A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insightscited by 24
- 2021More Real than Real: A Study on Human Visual Perception of Synthetic Facescited by 23
- 2024Gaussian Eigen Models for Human Headscited by 21
- 2023Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localizationcited by 20
- 2023StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generationcited by 19
- 2024Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approachcited by 18
- 2022Exposing Deepfake Face Forgeries with Guided Residualscited by 17
- 2023Emotional Listener Portrait: Neural Listener Head Generation with Emotioncited by 17
- 2024Joker: Conditional 3D Head Synthesis with Extreme Facial Expressionscited by 17
- 2024PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Datasetcited by 16
- 2021Detection and Localization of Facial Expression Manipulationscited by 15
- 2022Testing Human Ability To Detect Deepfake Images of Human Facescited by 15
- 2021A Study of the Human Perception of Synthetic Facescited by 14
- 2025Synthetic Prior for Few-Shot Drivable Head Avatar Inversioncited by 14
- 2022A Review of Deep Learning-based Approaches for Deepfake Content Detectioncited by 12
50 most cited of 118 All 118 (JSON)
- 2026Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation8 Aug 2026
- 2026VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection7 Jul 2026
- 2026FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image23 Jun 2026
- 2026Robust Deepfake Detection: Mitigating Spatial Attention Drift via Calibrated Complementary Ensembles28 Apr 2026
- 20263DRealHead: Few-Shot Detailed Head Avatar14 Apr 2026
- 2026Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity8 Apr 2026
- 2026Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection25 Mar 2026
- 2026SAiW: Source-Attributable Invisible Watermarking for Proactive Deepfake Defense24 Mar 2026
- 2026FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation10 Mar 2026
- 2026Deepfake Synthesis vs. Detection: An Uneven Contest8 Feb 2026
- 2026ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation15 Jan 2026
- 2025Performance Decay in Deepfake Detection: The Limitations of Training on Outdated Data10 Nov 2025
38 more
- 2025A Dual-Branch CNN for Robust Detection of AI-Generated Facial Forgeries28 Oct 2025
- 2025Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders11 Sep 2025
- 2025Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning27 Aug 2025
- 2025Geometry-Aware Video Inpainting for Joint Headset Occlusion Removal and Face Reconstruction in Social XR17 Aug 2025
- 2025Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis21 Jul 2025
- 2025Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection3 Jul 2025
- 2025AuthGuard: Generalizable Deepfake Detection via Language Guidance4 Jun 2025
- 2025CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs27 May 2025
- 2025DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation9 Apr 2025
- 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion10 Mar 2025
- 2025Controllable Video Generation with Provable Disentanglement4 Feb 2025
- 2025GC-ConsFlow: Leveraging Optical Flow Residuals and Global Context for Robust Deepfake Detection23 Jan 2025
- 2025Synthetic Prior for Few-Shot Drivable Head Avatar Inversion12 Jan 2025
- 2024SparseDiT: Token Sparsification for Efficient Diffusion Transformer8 Dec 2024
- 2024Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints26 Nov 2024
- 2024Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation24 Nov 2024
- 2024Improved Video VAE for Latent Video Diffusion Model10 Nov 2024
- 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectors6 Nov 2024
- 2024Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions21 Oct 2024
- 2024Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach4 Oct 2024
- 2024COMUNI: Decomposing Common and Unique Video Signals for Diffusion-based Video Generation2 Oct 2024
- 2024The DeepSpeak Dataset9 Aug 2024
- 2024Segment Anything for Videos: A Systematic Survey31 Jul 2024
- 2024AU-vMAE: Knowledge-Guide Action Units Detection via Video Masked Autoencoder16 Jul 2024
- 2024A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights11 Jul 2024
- 2024Gaussian Eigen Models for Human Heads5 Jul 2024
- 2024PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset14 May 2024
- 2024Matten: Video Generation with Mamba-Attention5 May 2024
- 2024Dyadic Interaction Modeling for Social Behavior Generation14 Mar 2024
- 2024Headset: Human emotion awareness under partial occlusions multimodal dataset14 Feb 2024
- 2024Towards Realistic Landmark-Guided Facial Video Inpainting Based on GANs14 Feb 2024
- 2024One-shot Neural Face Reenactment via Finding Directions in GAN's Latent Space5 Feb 2024
- 2024GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning3 Feb 2024
- 2024Masked Conditional Diffusion Model for Enhancing Deepfake Detection1 Feb 2024
- 2024Expression-aware video inpainting for HMD removal in XR applications25 Jan 2024
- 2024RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks11 Jan 2024
- 2024Deep Learning-based Image and Video Inpainting: A Survey7 Jan 2024
- 2024Latte: Latent Diffusion Transformer for Video Generation5 Jan 2024
50 newest of 118 All 118 (JSON)
- 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
- 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 180
- 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusioncited by 53
- 2024Improved Video VAE for Latent Video Diffusion Modelcited by 46
- 2024Matten: Video Generation with Mamba-Attentioncited by 24
- 2024Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approachcited by 18
- 2024Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraintscited by 11
- 2024Masked Conditional Diffusion Model for Enhancing Deepfake Detectioncited by 9
- 2024SparseDiT: Token Sparsification for Efficient Diffusion Transformercited by 9
- 2024Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generationcited by 2
- 2025Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoderscited by 2
- 2025DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generationcited by 1
12 most cited of 15 All 15 (JSON)
- 2026FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image23 Jun 2026
- 2026FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation10 Mar 2026
- 2025Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders11 Sep 2025
- 2025DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation9 Apr 2025
- 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion10 Mar 2025
- 2024SparseDiT: Token Sparsification for Efficient Diffusion Transformer8 Dec 2024
- 2024Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints26 Nov 2024
- 2024Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation24 Nov 2024
- 2024Improved Video VAE for Latent Video Diffusion Model10 Nov 2024
- 2024Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach4 Oct 2024
- 2024COMUNI: Decomposing Common and Unique Video Signals for Diffusion-based Video Generation2 Oct 2024
- 2024Matten: Video Generation with Mamba-Attention5 May 2024
12 newest of 15 All 15 (JSON)
- 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
- 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
- 2021Neural Head Avatars from Monocular RGB Videoscited by 212
- 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
- 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
- 2022Generating Long Videos of Dynamic Scenescited by 113
- 2021Representative Forgery Mining for Fake Face Detectioncited by 108
- 2021One Shot Face Swapping on Megapixelscited by 105
- 2023CelebV-Text: A Large-Scale Facial Text-Video Datasetcited by 103
- 2023Emotional Speech-Driven Animation with Content-Emotion Disentanglementcited by 98
- 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
- 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
12 most cited of 100 All 100 (JSON)
- 2026Robust Deepfake Detection: Mitigating Spatial Attention Drift via Calibrated Complementary Ensembles28 Apr 2026
- 20263DRealHead: Few-Shot Detailed Head Avatar14 Apr 2026
- 2026Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity8 Apr 2026
- 2026Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection25 Mar 2026
- 2026Deepfake Synthesis vs. Detection: An Uneven Contest8 Feb 2026
- 2026ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation15 Jan 2026
- 2025Performance Decay in Deepfake Detection: The Limitations of Training on Outdated Data10 Nov 2025
- 2025A Dual-Branch CNN for Robust Detection of AI-Generated Facial Forgeries28 Oct 2025
- 2025Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning27 Aug 2025
- 2025Geometry-Aware Video Inpainting for Joint Headset Occlusion Removal and Face Reconstruction in Social XR17 Aug 2025
- 2025Uncovering Critical Features for Deepfake Detection through the Lottery Ticket Hypothesis21 Jul 2025
- 2025Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection3 Jul 2025
12 newest of 100 All 100 (JSON)