paper-with-me

Papers

Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection

2025-07-03 · TaeHoon Kim, Jongwook Choi, Yonghyun Jeong, Haeun Noh, Jaejun Yoo, Seungryul Baek, Jongwon Choi

We introduce a deepfake video detection approach that exploits pixel-wise temporal inconsistencies, which traditional spatial frequency-based detectors often overlook. Traditional detectors represent temporal information merely by stacking spatial frequency spectra across frames, resulting in the failure to detect temporal artifacts in the pixel plane. Our approach performs a 1D Fourier transform on the time axis for each pixel, extracting features highly sensitive to temporal inconsistencies, especially in areas prone to unnatural movements. To precisely locate regions containing the temporal artifacts, we introduce an attention proposal module trained in an end-to-end manner. Additionally, our joint transformer module effectively integrates pixel-wise temporal frequency features with spatio-temporal context features, expanding the range of detectable forgery artifacts. Our framework represents a significant advancement in deepfake video detection, providing robust performance across diverse and challenging detection scenarios.

📄 PDF Abstract BibTeX arXiv:2507.02398

Code (1)

rama0126/pwtf-dvd 공식 구현

Tasks

Face Swapping

Similar Papers 제목 키워드 기반

Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction

2020-02-23 · CVPR 2020 6 · Beibei Jin, Yu Hu, Qiankun Tang, Jingyu Niu 외

Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to ima…

PredictionVideo GenerationVideo Prediction

Defending Against Frequency-Based Attacks with Diffusion Models

2025-04-15 · Fatemeh Amerehi, Patrick Healy

Adversarial training is a common strategy for enhancing model robustness against adversarial attacks. However, it is typically tailored to the specific attack types it is trained on, limiting its ability to generalize to…

Adversarial Purification

Self-Supervised Temporal Analysis of Spatiotemporal Data

2023-04-25 · Yi Cao, Swetava Ganguli, Vipul Pandey

There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to stratify landscape based on mobility activity time series. First, the time se…

Semantic SegmentationTime Series

FADRA: Frequency-Aware Diffusion with Residual Adaptation for Video Face Restoration

2026-07-07 · Jin Jiang, Jia Wang, Panwen Hu, Weiran Zhao 외 arxiv

Video face restoration (VFR) aims to recover high-quality and temporally consistent facial details from severely degraded video sequences; however, existing methods still struggle to balance spatial fidelity and temporal…

Efficient Video Deblurring Guided by Motion Magnitude

2022-07-27 · Yusheng Wang, Yunfan Lu, Ye Gao, Lin Wang 외

Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame;…

DeblurringOptical Flow EstimationVideo Deblurring