RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos

• URL: http://arxiv.org/abs/2403.10058v1
• Date: Fri, 15 Mar 2024 06:59:21 GMT
• Title: RID-TWIN: An end-to-end pipeline for automatic face de-identification in videos
• Authors: Anirban Mukherjee, Monjoy Narayan Choudhury, Dinesh Babu Jayagopi,
• Abstract summary: RID-Twin is a pipeline that decouples identity from motion to perform automatic face de-identification in videos. We evaluate the performance of our methodology on the widely employed VoxCeleb2 dataset.
• Score: 2.7569134765233536
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Face de-identification in videos is a challenging task in the domain of computer vision, primarily used in privacy-preserving applications. Despite the considerable progress achieved through generative vision models, there remain multiple challenges in the latest approaches. They lack a comprehensive discussion and evaluation of aspects such as realism, temporal coherence, and preservation of non-identifiable features. In our work, we propose RID-Twin: a novel pipeline that leverages the state-of-the-art generative models, and decouples identity from motion to perform automatic face de-identification in videos. We investigate the task from a holistic point of view and discuss how our approach addresses the pertinent existing challenges in this domain. We evaluate the performance of our methodology on the widely employed VoxCeleb2 dataset, and also a custom dataset designed to accommodate the limitations of certain behavioral variations absent in the VoxCeleb2 dataset. We discuss the implications and advantages of our work and suggest directions for future research.

Related papers

• Privacy-Preserving Video Anomaly Detection: A Survey [10.899433437231139]
  Video Anomaly Detection (VAD) aims to automatically analyze patterns in surveillance videos collected from open spaces to detect anomalous events that may cause harm without physical contact. The lack of transparency in video transmission and usage raises public concerns about privacy and ethics limiting the real-world application of VAD. Recently, researchers have focused on privacy concerns in VAD by conducting systematic studies from various perspectives including data, features, and systems. This article systematically reviews progress in P2VAD for the first time, defining its scope and providing an intuitive taxonomy.
  arXiv  Detail & Related papers  (2024-11-21T20:29:59Z)
• Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases [69.46487306858789]
  Conditional Autoregressive Slot Attention (CA-SA) is a framework that enhances the temporal consistency of extracted object-centric representations in video-centric vision tasks. We present qualitative and quantitative results showing that our proposed method outperforms the considered baselines on downstream tasks.
  arXiv  Detail & Related papers  (2024-10-21T07:44:44Z)
• Deep Learning-Based Object Pose Estimation: A Comprehensive Survey [73.74933379151419]
  We discuss the recent advances in deep learning-based object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks.
  arXiv  Detail & Related papers  (2024-05-13T14:44:22Z)
• Deepfake Generation and Detection: A Benchmark and Survey [134.19054491600832]
  Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions. This survey comprehensively reviews the latest developments in deepfake generation and detection. We focus on researching four representative deepfake fields: face swapping, face reenactment, talking face generation, and facial attribute editing.
  arXiv  Detail & Related papers  (2024-03-26T17:12:34Z)
• Attribute-preserving Face Dataset Anonymization via Latent Code Optimization [64.4569739006591]
  We present a task-agnostic anonymization procedure that directly optimize the images' latent representation in the latent space of a pre-trained GAN. We demonstrate through a series of experiments that our method is capable of anonymizing the identity of the images whilst -- crucially -- better-preserving the facial attributes.
  arXiv  Detail & Related papers  (2023-03-20T17:34:05Z)
• A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design [77.34726150561087]
  We conduct a survey on the most relevant and recent advances in Deep Semantic in the context of vision for autonomous vehicles. Our main objective is to provide a comprehensive discussion on the main methods, advantages, limitations, results and challenges faced from each perspective.
  arXiv  Detail & Related papers  (2023-03-08T01:29:55Z)
• StyleID: Identity Disentanglement for Anonymizing Faces [4.048444203617942]
  The main contribution of the paper is the design of a feature-preserving anonymization framework, StyleID. As part of the contribution, we present a novel disentanglement metric, three complementing disentanglement methods, and new insights into identity disentanglement. StyleID provides tunable privacy, has low computational complexity, and is shown to outperform current state-of-the-art solutions.
  arXiv  Detail & Related papers  (2022-12-28T12:04:24Z)
• Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making [66.72253432908693]
  Kinship recognition is a challenging problem with many practical applications. We review the public resources and data challenges that enabled and inspired many to hone-in on the views. For the tenth anniversary, the demo code is provided for the various kin-based tasks.
  arXiv  Detail & Related papers  (2020-06-29T13:25:45Z)
• CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks [12.20367903755194]
  CIAGAN is a model for image and video anonymization based on conditional generative adversarial networks. Our model is able to remove the identifying characteristics of faces and bodies while producing high-quality images and videos.
  arXiv  Detail & Related papers  (2020-05-19T15:56:08Z)

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.