Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

• URL: http://arxiv.org/abs/2605.21977v1
• Date: Thu, 21 May 2026 04:11:32 GMT
• Title: Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection
• Abstract summary: We show that SOTA AI-generated image detectors often collapse when applied to frames extracted from videos.<n>Motivated by these findings, we propose VINA, a unified AIGC detection framework that jointly trains on image and video data.
• Score: 17.82437958396922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and visual modalities. A strongly generalizable detector should remain robust under distributional variations. However, we identify a consistent failure mode: SOTA AI-generated image detectors often collapse when applied to frames extracted from videos. Through systematic analysis, we show that this cross-modal gap arises from both entangled synthesis-agnostic video processing shifts, including color conversion, codec compression, resizing, and blur, and model-specific fingerprints introduced by modern video generators. Motivated by these findings, we propose VINA (Video as Natural Augmentation), a unified AIGC detection framework that jointly trains on image and video data. VINA uses video frames as physically grounded natural augmentations and further introduces a cross-modal supervised contrastive objective to align image and video representations under a shared real/fake decision boundary. Extensive experiments on 14 image, video, and in-the-wild benchmarks show that VINA delivers bidirectional gains, improves robustness and transferability, and achieves state-of-the-art performance across nearly all evaluated settings without complex augmentation or dataset-specific tuning.

Related papers

• Learning Unified Video and Image Representation for Video Face Forgery Detection [49.19035628283472]
  Existing methods for video face forgery detection assume that all frames in a forged video are manipulated.<n>We propose a novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos.<n>UVIF employs a unified encoder and a multi-task learning paradigm to jointly model facial videos and images for boosted video face forgery detection.
  arXiv  Detail & Related papers  (2026-08-13T10:25:59Z)
• Revealing Artifacts via Noise Amplification: A Novel Perspective for AI-Generated Video Detection [25.492080916045012]
  A novel approach called Noise Amplification is proposed to detect AI-generated videos.<n>Noise amplification is constructed by incorporating three aspects: pixel-level intensity enhancement, region-level spatial amplification, and frame-level temporal aggregation.<n>Our experiments show that our simple approach significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-06-15T14:04:17Z)
• CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection [45.739302264021795]
  Video synthesis techniques pose an unprecedented challenge to digital authenticity.<n>We identify a distinctive fingerprint in cross-modal temporal artifact (CMTA)<n>We propose the CMTA framework, a cross-modal detection approach that captures these unique temporal artifacts.
  arXiv  Detail & Related papers  (2026-05-01T13:04:14Z)
• ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity [44.13741922118129]
  We identify a distinctive fingerprint in AIGVs, termed anomalous temporal self-similarity (ATSS)<n>We propose ATSS, a multimodal detection framework that exploits this insight via a triple-similarity representation and a cross-attentive fusion mechanism.<n>ATSS significantly outperforms state-of-the-art methods in terms of AP, AUC, and ACC metrics.
  arXiv  Detail & Related papers  (2026-04-05T09:10:13Z)
• CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion [62.04833878126661]
  We tackle the dual challenges of video understanding and controllable video generation within a unified diffusion framework.<n>We propose CtrlVDiff, a unified diffusion model trained with a Hybrid Modality Control Strategy (HMCS) that routes and fuses features from depth, normals, segmentation, edges, and graphics-based intrinsics (albedo, roughness, metallic)<n>Across understanding and generation benchmarks, CtrlVDiff delivers superior controllability and fidelity, enabling layer-wise edits (relighting, material adjustment, object insertion) and surpassing state-of-the-art baselines while remaining robust when some modalities are unavailable.
  arXiv  Detail & Related papers  (2025-11-26T07:27:11Z)
• Video Forgery Detection with Optical Flow Residuals and Spatial-Temporal Consistency [1.7061868168035932]
  We propose a detection framework that leverages spatial-temporal consistency by combining RGB appearance features with optical flow residuals.<n>By integrating these complementary features, the proposed method effectively detects a wide range of forged videos.
  arXiv  Detail & Related papers  (2025-08-01T07:51:35Z)
• DAVID-XR1: Detecting AI-Generated Videos with Explainable Reasoning [58.70446237944036]
  DAVID-X is the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales.<n>We present DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning.<n>Our results highlight the promise of explainable detection methods for trustworthy identification of AI-generated video content.
  arXiv  Detail & Related papers  (2025-06-13T13:39:53Z)
• IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection [24.67072921674199]
  We introduce IVY-FAKE, a novel, unified, and large-scale dataset for explainable multimodal AIGC detection.<n>We propose Ivy Explainable Detector (IVY-XDETECTOR), a unified AIGC detection and explainable architecture.<n>Our unified vision-language model achieves state-of-the-art performance across multiple image and video detection benchmarks.
  arXiv  Detail & Related papers  (2025-06-01T12:20:22Z)
• BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation [77.55074597806035]
  GenBuster-200K is a large-scale, high-quality AI-generated video dataset featuring 200K high-resolution video clips.<n>BusterX is a novel AI-generated video detection and explanation framework leveraging multimodal large language model (MLLM) and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-19T02:06:43Z)
• CANeRV: Content Adaptive Neural Representation for Video Compression [89.35616046528624]
  We propose Content Adaptive Neural Representation for Video Compression (CANeRV)<n>CANeRV is an innovative INR-based video compression network that adaptively conducts structure optimisation based on the specific content of each video sequence.<n>We show that CANeRV can outperform both H.266/VVC and state-of-the-art INR-based video compression techniques across diverse video datasets.
  arXiv  Detail & Related papers  (2025-02-10T06:21:16Z)
• TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation [97.96178992465511]
  We argue that generated videos should incorporate the emergence of new concepts and their relation transitions like in real-world videos as time progresses. To assess the Temporal Compositionality of video generation models, we propose TC-Bench, a benchmark of meticulously crafted text prompts, corresponding ground truth videos, and robust evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-12T21:41:32Z)
• An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal [99.49099501559652]
  Video Coding for Machine (VCM) aims to bridge the gap between visual feature compression and classical video coding. We employ a conditional deep generation network to reconstruct video frames with the guidance of learned motion pattern. By learning to extract sparse motion pattern via a predictive model, the network elegantly leverages the feature representation to generate the appearance of to-be-coded frames.
  arXiv  Detail & Related papers  (2020-01-09T14:18:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.