paper-with-me

홈 › Papers

Temporally coherent video anonymization through GAN inpainting

2021-06-04 · Thangapavithraa Balaji, Patrick Blies, Georg Göri, Raphael Mitsch, Marcel Wasserer, Torsten Schön

This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individual frames of the video. The second stage leverages a privacy-preserving Video Generative Adversarial Network designed to inpaint the missing image patches with artificially generated faces. Our initial experiments reveal that image based generative models are not capable of inpainting patches showing temporal coherent appearance across neighboring video frames. To address this issue we introduce a newly curated video collection, which is made publicly available for the research community along with this paper. We also introduce the Identity Invariance Score IdI as a means to quantify temporal coherency between neighboring frames.

📄 PDF Abstract BibTeX arXiv:2106.02328

Code (0)

등록된 구현이 없습니다.

Tasks

Face AnonymizationGenerative Adversarial NetworkPrivacy Preserving

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

BLANKET: Anonymizing Faces in Infant Video Recordings

2025-12-17 · Ditmar Hadera, Jan Cech, Miroslav Purkrabek, Matej Hoffmann arxiv

Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consis…

Keypoint DetectionPose EstimationFace Swapping

Optimised ProPainter for Video Diminished Reality Inpainting

2024-06-04 · Pengze Li, Lihao Liu, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero

In this paper, part of the DREAMING Challenge - Diminished Reality for Emerging Applications in Medicine through Inpainting, we introduce a refined video inpainting technique optimised from the ProPainter method to meet …

Video Inpainting

Deep Flow-Guided Video Inpainting

2019-05-08 · CVPR 2019 6 · Rui Xu, Xiaoxiao Li, Bolei Zhou, Chen Change Loy

Video inpainting, which aims at filling in missing regions of a video, remains challenging due to the difficulty of preserving the precise spatial and temporal coherence of video contents. In this work we propose a novel…

One-shot visual object segmentationOptical Flow EstimationVideo fixed region InpaintingVideo Inpainting

Copy-and-Paste Networks for Deep Video Inpainting

2019-08-30 · ICCV 2019 10 · Sungho Lee, Seoung Wug Oh, DaeYeun Won, Seon Joo Kim

We present a novel deep learning based algorithm for video inpainting. Video inpainting is a process of completing corrupted or missing regions in videos. Video inpainting has additional challenges compared to image inpa…

Image InpaintingLane DetectionVideo Inpainting

Decoupled Spatial-Temporal Transformer for Video Inpainting

2021-04-14 · Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi 외

Video inpainting aims to fill the given spatiotemporal holes with realistic appearance but is still a challenging task even with prosperous deep learning approaches. Recent works introduce the promising Transformer archi…

Video Inpainting