One-Shot Identity-Preserving Portrait Reenactment

• URL: http://arxiv.org/abs/2004.12452v1
• Date: Sun, 26 Apr 2020 18:30:33 GMT
• Title: One-Shot Identity-Preserving Portrait Reenactment
• Authors: Sitao Xiang, Yuming Gu, Pengda Xiang, Mingming He, Koki Nagano, Haiwei Chen, Hao Li
• Abstract summary: We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. We aim to address identity preservation in cross-subject portrait reenactment from a single picture.
• Score: 16.889479797252783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a deep learning-based framework for portrait reenactment from a single picture of a target (one-shot) and a video of a driving subject. Existing facial reenactment methods suffer from identity mismatch and produce inconsistent identities when a target and a driving subject are different (cross-subject), especially in one-shot settings. In this work, we aim to address identity preservation in cross-subject portrait reenactment from a single picture. We introduce a novel technique that can disentangle identity from expressions and poses, allowing identity preserving portrait reenactment even when the driver's identity is very different from that of the target. This is achieved by a novel landmark disentanglement network (LD-Net), which predicts personalized facial landmarks that combine the identity of the target with expressions and poses from a different subject. To handle portrait reenactment from unseen subjects, we also introduce a feature dictionary-based generative adversarial network (FD-GAN), which locally translates 2D landmarks into a personalized portrait, enabling one-shot portrait reenactment under large pose and expression variations. We validate the effectiveness of our identity disentangling capabilities via an extensive ablation study, and our method produces consistent identities for cross-subject portrait reenactment. Our comprehensive experiments show that our method significantly outperforms the state-of-the-art single-image facial reenactment methods. We will release our code and models for academic use.

Related papers

• AniFaceDiff: High-Fidelity Face Reenactment via Facial Parametric Conditioned Diffusion Models [33.39336530229545]
  Face reenactment refers to the process of transferring the pose and facial expressions from a reference (driving) video onto a static facial (source) image. Previous research in this domain has made significant progress by training controllable deep generative models to generate faces. This paper proposes a new method based on Stable Diffusion, called AniFaceDiff, incorporating a new conditioning module for high-fidelity face reenactment.
  arXiv  Detail & Related papers  (2024-06-19T07:08:48Z)
• PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization [92.90392834835751]
  PortraitBooth is designed for high efficiency, robust identity preservation, and expression-editable text-to-image generation. PortraitBooth eliminates computational overhead and mitigates identity distortion. It incorporates emotion-aware cross-attention control for diverse facial expressions in generated images.
  arXiv  Detail & Related papers  (2023-12-11T13:03:29Z)
• HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces [47.27033282706179]
  We present our method for neural face reenactment, called HyperReenact, that aims to generate realistic talking head images of a source identity. Our method operates under the one-shot setting (i.e., using a single source frame) and allows for cross-subject reenactment, without requiring subject-specific fine-tuning. We compare our method both quantitatively and qualitatively against several state-of-the-art techniques on the standard benchmarks of VoxCeleb1 and VoxCeleb2.
  arXiv  Detail & Related papers  (2023-07-20T11:59:42Z)
• Facial Reenactment Through a Personalized Generator [47.02774886256621]
  We propose a novel method for facial reenactment using a personalized generator. We locate the desired frames in the latent space of the personalized generator using carefully designed latent optimization. We show that since our reenactment takes place in a semantic latent space, it can be semantically edited and stylized in post-processing.
  arXiv  Detail & Related papers  (2023-07-12T17:09:18Z)
• StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment [47.27033282706179]
  We propose a framework that learns to disentangle the identity characteristics of the face from its pose. We show that the proposed method produces higher quality results even on extreme pose variations.
  arXiv  Detail & Related papers  (2022-09-27T13:22:35Z)
• Graph-based Generative Face Anonymisation with Pose Preservation [49.18049578591058]
  AnonyGAN is a GAN-based solution for face anonymisation. It replaces the visual information corresponding to a source identity with a condition identity provided as any single image.
  arXiv  Detail & Related papers  (2021-12-10T12:58:17Z)
• LI-Net: Large-Pose Identity-Preserving Face Reenactment Network [14.472453602392182]
  We propose a large-pose identity-preserving face reenactment network, LI-Net. Specifically, the Landmark Transformer is adopted to adjust driving landmark images. The Face Rotation Module and the Expression Enhancing Generator decouple the transformed landmark image into pose and expression features, and reenact those attributes separately to generate identity-preserving faces.
  arXiv  Detail & Related papers  (2021-04-07T01:41:21Z)
• ActGAN: Flexible and Efficient One-shot Face Reenactment [1.8431600219151503]
  ActGAN is a novel end-to-end generative adversarial network (GAN) for one-shot face reenactment. We introduce a "many-to-many" approach, which allows arbitrary persons both for source and target without additional retraining. We also introduce a solution to preserve a person's identity between synthesized and target person by adopting the state-of-the-art approach in deep face recognition domain.
  arXiv  Detail & Related papers  (2020-03-30T22:03:16Z)
• Towards Face Encryption by Generating Adversarial Identity Masks [53.82211571716117]
  We propose a targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks. TIP-IM provides 95%+ protection success rate against various state-of-the-art face recognition models.
  arXiv  Detail & Related papers  (2020-03-15T12:45:10Z)

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.