FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face Extraction

• URL: http://arxiv.org/abs/2201.08425v1
• Date: Thu, 20 Jan 2022 19:44:18 GMT
• Title: FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face Extraction
• Authors: Xiangnan Yin and Liming Chen
• Abstract summary: Occlusions often occur in face images in the wild, troubling face-related tasks such as landmark detection, 3D reconstruction, and face recognition. This paper proposes a novel face segmentation dataset with manually labeled face occlusions from the CelebA-HQ and the internet. We trained a straightforward face segmentation model but obtained SOTA performance, convincingly demonstrating the effectiveness of the proposed dataset.
• Score: 3.8502825594372703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Occlusions often occur in face images in the wild, troubling face-related tasks such as landmark detection, 3D reconstruction, and face recognition. It is beneficial to extract face regions from unconstrained face images accurately. However, current face segmentation datasets suffer from small data volumes, few occlusion types, low resolution, and imprecise annotation, limiting the performance of data-driven-based algorithms. This paper proposes a novel face occlusion dataset with manually labeled face occlusions from the CelebA-HQ and the internet. The occlusion types cover sunglasses, spectacles, hands, masks, scarfs, microphones, etc. To the best of our knowledge, it is by far the largest and most comprehensive face occlusion dataset. Combining it with the attribute mask in CelebAMask-HQ, we trained a straightforward face segmentation model but obtained SOTA performance, convincingly demonstrating the effectiveness of the proposed dataset.

Related papers

• DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis [71.40724659748787]
  DiffusionFace is the first diffusion-based face forgery dataset. It covers various forgery categories, including unconditional and Text Guide facial image generation, Img2Img, Inpaint, and Diffusion-based facial exchange algorithms. It provides essential metadata and a real-world internet-sourced forgery facial image dataset for evaluation.
  arXiv  Detail & Related papers  (2024-03-27T11:32:44Z)
• Mask-FPAN: Semi-Supervised Face Parsing in the Wild With De-Occlusion and UV GAN [9.433856779172064]
  Mask-FPAN is a novel framework that learns to parse occluded faces in a semi-supervised way. A 3D morphable face model combined with the UV GAN improves the robustness of 2D face parsing. We introduce two new datasets named FaceOcc-MaskHQ and CelebAMaskOcc-HQ for face paring work.
  arXiv  Detail & Related papers  (2022-12-18T14:51:46Z)
• FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders [81.21440457805932]
  We propose a novel framework FaceMAE, where the face privacy and recognition performance are considered simultaneously. randomly masked face images are used to train the reconstruction module in FaceMAE. We also perform sufficient privacy-preserving face recognition on several public face datasets.
  arXiv  Detail & Related papers  (2022-05-23T07:19:42Z)
• Segmentation-Reconstruction-Guided Facial Image De-occlusion [48.952656891182826]
  Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. This paper proposes a novel face de-occlusion model based on face segmentation and 3D face reconstruction.
  arXiv  Detail & Related papers  (2021-12-15T10:40:08Z)
• End2End Occluded Face Recognition by Masking Corrupted Features [82.27588990277192]
  State-of-the-art general face recognition models do not generalize well to occluded face images. This paper presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks.
  arXiv  Detail & Related papers  (2021-08-21T09:08:41Z)
• Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection [65.92058628082322]
  Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. This paper presents a novel Learning to Aggregate and Personalize framework for unsupervised robust 3D face modeling.
  arXiv  Detail & Related papers  (2021-06-15T03:10:17Z)
• Towards NIR-VIS Masked Face Recognition [47.00916333095693]
  Near-infrared to visible (NIR-VIS) face recognition is the most common case in heterogeneous face recognition. We propose a novel training method to maximize the mutual information shared by the face representation of two domains. In addition, a 3D face reconstruction based approach is employed to synthesize masked face from the existing NIR image.
  arXiv  Detail & Related papers  (2021-04-14T10:40:09Z)
• When Face Recognition Meets Occlusion: A New Benchmark [37.616211206620854]
  We create a simulated occlusion face recognition dataset. It covers 804,704 face images of 10,575 subjects. Our dataset significantly outperforms the state-of-the-arts.
  arXiv  Detail & Related papers  (2021-03-04T03:07:42Z)
• Masked Face Recognition Dataset and Application [28.2082082956263]
  This work proposes three types of masked face datasets, including Masked Face Detection dataset (MFDD), Real-world Masked Face Recognition dataset (RMFRD) and Simulated Masked Face Recognition dataset (SMFRD) The multi-granularity masked face recognition model we developed achieves 95% accuracy, exceeding the results reported by the industry.
  arXiv  Detail & Related papers  (2020-03-20T04:15:19Z)

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.