ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2302.07848
19
3

One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2

15 February 2023
Trevine Oorloff
Yaser Yacoob
    CVBM
ArXivPDFHTML
Abstract

While recent research has progressively overcome the low-resolution constraint of one-shot face video re-enactment with the help of StyleGAN's high-fidelity portrait generation, these approaches rely on at least one of the following: explicit 2D/3D priors, optical flow based warping as motion descriptors, off-the-shelf encoders, etc., which constrain their performance (e.g., inconsistent predictions, inability to capture fine facial details and accessories, poor generalization, artifacts). We propose an end-to-end framework for simultaneously supporting face attribute edits, facial motions and deformations, and facial identity control for video generation. It employs a hybrid latent-space that encodes a given frame into a pair of latents: Identity latent, WID\mathcal{W}_{ID}WID​, and Facial deformation latent, SF\mathcal{S}_FSF​, that respectively reside in the W+W+W+ and SSSSSS spaces of StyleGAN2. Thereby, incorporating the impressive editability-distortion trade-off of W+W+W+ and the high disentanglement properties of SSSSSS. These hybrid latents employ the StyleGAN2 generator to achieve high-fidelity face video re-enactment at 102421024^210242. Furthermore, the model supports the generation of realistic re-enactment videos with other latent-based semantic edits (e.g., beard, age, make-up, etc.). Qualitative and quantitative analyses performed against state-of-the-art methods demonstrate the superiority of the proposed approach.

View on arXiv
Comments on this paper