PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 5, 2026IEEE Transactions on Pattern Analysis and Machine Intelligence4 citations

UniFES: A Unified Recurrent Network for Quality Enhancement and Stabilization in Face Videos

View Full Paper
TLTie LiuMXMai XuSLShengxi Li

Key Points

  • To develop a unified recurrent network for enhancing quality and stabilizing motion in face videos.
  • Proposed UniFES network for joint video quality enhancement and stabilization.
  • Decomposed shaking temporal alignment into progressive feature alignment.
  • Integrated mixed dynamics from both pixel and motion domains for stabilization.
  • Established a synthetic dataset for training and evaluation.
  • Demonstrated superior performance over 32 baseline methods on synthetic datasets.
  • Achieved high-quality full frame rendering and robust trajectory estimation.

Abstract

Recent years have witnessed an explosive increase of face content, which drives a distinct shift from static images to dynamic video formats. The shift of formats inherently alters the characteristics within face videos, whereby pixel-wise artifacts are intertwined with motion-related impairments. Addressing the emerging distortions that now always appear by twins in practice, however, is challenging and non-trivial, due to the distinct characteristics in addressing spatial-temporal frequencies in videos. In this paper, we propose a novel Unified recurrent network for joint Face video quality Enhancement and Stabilization (UniFES), as the first successful attempt for both quality enhancement and motion stabilization. Correspondingly, our UniFES method proposes to effectively aggregate the mutual information in the pixel and motion domains. For the quality enhancement, our UniFES method decomposes the shaking temporal alignment problem into progressive feature alignment with explicit physical information, which includes the global dynamics from the motion domain, i.e., from the stabilization task. Regarding the video stabilization, we integrate the mixed dynamics from the enhancement task (i.e., from pixel domain) to take into account both pixel-wise and motion-related characteristics, for ensuring robust trajectory estimation and motion stabilization. Subsequently, we refine the warping masks to achieve high-quality full frame rendering. We further establish a synthetic dataset for training and evaluation regarding this emerging task. Comprehensive experiments have illustrated the superior performances of our UniFES method over 32 comparing baselines on both newly established synthetic and real-world datasets.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69a91d21d6127c7a504bffb5https://doi.org/10.1109/tpami.2026.3669431
Ask AI
Helpful
Bookmark
Share
View Full Paper