Uncertainty-Guided Face Matting for Occlusion-Aware Face Transformation

• URL: http://arxiv.org/abs/2508.03055v1
• Date: Tue, 05 Aug 2025 04:00:14 GMT
• Title: Uncertainty-Guided Face Matting for Occlusion-Aware Face Transformation
• Authors: Hyebin Cho, Jaehyup Lee,
• Abstract summary: Face filters have become a key element of short-form video content, enabling a wide array of visual effects such as stylization and face swapping.<n>We introduce the novel task of face matting, which estimates fine-grained alpha mattes to separate occluding elements from facial regions.<n>We present FaceMat, a trimap-free, uncertainty-aware framework that predicts high-quality alpha mattes under complex occlusions.
• Score: 1.4195677954898822
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Face filters have become a key element of short-form video content, enabling a wide array of visual effects such as stylization and face swapping. However, their performance often degrades in the presence of occlusions, where objects like hands, hair, or accessories obscure the face. To address this limitation, we introduce the novel task of face matting, which estimates fine-grained alpha mattes to separate occluding elements from facial regions. We further present FaceMat, a trimap-free, uncertainty-aware framework that predicts high-quality alpha mattes under complex occlusions. Our approach leverages a two-stage training pipeline: a teacher model is trained to jointly estimate alpha mattes and per-pixel uncertainty using a negative log-likelihood (NLL) loss, and this uncertainty is then used to guide the student model through spatially adaptive knowledge distillation. This formulation enables the student to focus on ambiguous or occluded regions, improving generalization and preserving semantic consistency. Unlike previous approaches that rely on trimaps or segmentation masks, our framework requires no auxiliary inputs making it well-suited for real-time applications. In addition, we reformulate the matting objective by explicitly treating skin as foreground and occlusions as background, enabling clearer compositing strategies. To support this task, we newly constructed CelebAMat, a large-scale synthetic dataset specifically designed for occlusion-aware face matting. Extensive experiments show that FaceMat outperforms state-of-the-art methods across multiple benchmarks, enhancing the visual quality and robustness of face filters in real-world, unconstrained video scenarios. The source code and CelebAMat dataset are available at https://github.com/hyebin-c/FaceMat.git

Related papers

• CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models [57.9771859175664]
  Recent generative-prior-based methods have shown promising blind face restoration performance. Generating fine-grained facial details faithful to inputs remains a challenging problem. We introduce a diffusion-based-prior inside a VQGAN architecture that focuses on learning the distribution over uncorrupted latent embeddings.
  arXiv  Detail & Related papers  (2024-02-08T23:51:49Z)
• High-Fidelity Face Swapping with Style Blending [16.024260677867076]
  We propose an innovative end-to-end framework for high-fidelity face swapping. First, we introduce a StyleGAN-based facial attributes encoder that extracts essential features from faces and inverts them into a latent style code. Second, we introduce an attention-based style blending module to effectively transfer Face IDs from source to target.
  arXiv  Detail & Related papers  (2023-12-17T23:22:37Z)
• Occlusion-Aware Deep Convolutional Neural Network via Homogeneous Tanh-transforms for Face Parsing [2.062767930320204]
  Face parsing infers a pixel-wise label map for each semantic facial component. We propose a novel homogeneous tanh-transform for image preprocessing, which is made up of four tanh-transforms. Based on homogeneous tanh-transforms, we propose an occlusion-aware convolutional neural network for occluded face parsing.
  arXiv  Detail & Related papers  (2023-08-29T14:20:13Z)
• COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection [56.7599217711363]
  Face forgery recognition methods can only process one face at a time. Most face forgery recognition methods can only process one face at a time. We propose COMICS, an end-to-end framework for multi-face forgery detection.
  arXiv  Detail & Related papers  (2023-08-03T03:37:13Z)
• End-to-end Face-swapping via Adaptive Latent Representation Learning [12.364688530047786]
  This paper proposes a novel and end-to-end integrated framework for high resolution and attribute preservation face swapping. Our framework integrating facial perceiving and blending into the end-to-end training and testing process can achieve high realistic face-swapping on wild faces.
  arXiv  Detail & Related papers  (2023-03-07T19:16:20Z)
• FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face Extraction [3.8502825594372703]
  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.
  arXiv  Detail & Related papers  (2022-01-20T19:44:18Z)
• 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)
• Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails [53.080403912727604]
  We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN. It exploits facial geometry priors to replenish and upsample (8*) the occluded and tiny faces. Pro-UIGAN achieves visually pleasing HR faces, reaching superior performance in downstream tasks.
  arXiv  Detail & Related papers  (2021-08-02T02:29:24Z)
• 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)
• FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping [43.236261887752065]
  We propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. In its first stage, our framework generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. To address the challenging facial synthesiss, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net)
  arXiv  Detail & Related papers  (2019-12-31T17:57:46Z)

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.