cs.CVNov 9, 2026

MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection

Authors: Ahmed Y. Radwan, Shaina Raza

Organizations: Vector Institute for Artificial Intelligence Toronto, Canada

Abstract

Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature differences with adapted appearance representations improves detection across both forgery categories. We introduce Multiscale Appearance-Residual Streams (MARS), a two-path video detector. The residual path applies fixed spatial and temporal difference-of-Gaussians operators to frozen intermediate features and models the resulting differences alongside appearance context across frames. The semantic path adapts the encoder's normalization parameters for frame classification, and a clip-dependent gate combines their predictions. Under a shared protocol across seven datasets, MARS achieves the highest average AUROC of 91.43%, outperforming seven compared detectors. When trained on facial manipulations alone, MARS achieves 93.99% AUROC on GenVideo and 75.50% on DF26, demonstrating transfer to generated videos without generated-video training data. MARS also provides signed patch and frame contributions, whose faithfulness we evaluate through controlled spatial and temporal removal against random controls. MARS is publicly available for research: Project page: https://vectorinstitute.github.io/mars/ Github: https://github.com/VectorInstitute/mars

Figures & tables

Appendix figures & tables27 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. CAM-VFD: Cross-Attention Multimodal Video Forgery Detection

    May 16, 2026Hoda Osama Elkhodary, Sherin Mostafa Youssef, Marwa Elshenawy +1Multimodal Deepfake DetectionMultimodal Robustness

  2. Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints

    Apr 29, 2026Wasim Ahmad, Wei Zhang, Xuerui MaoAudio Deepfake DetectionCross-Modal Representation Learning

  3. Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection

    Mar 2, 2026Jianfeng Liao, Yichen Wei, Raymond Chan Ching Bon +3Deepfake DetectionDigital Image Forensics