Fresco++: Frequency-Guided and Canonical-Consistent Optimization for Fine-Grained Head Avatar Modeling

Key points

• Head avatar optimization is typically driven by per-view image supervision, which can lead to premature fitting of unstable high-frequency details and inconsistent local appearance across viewpoints.1
• Fresco++ addresses these challenges by regulating both the progression of visual detail and the formation of cross-view supervision during optimization.1
• For frequency-aware optimization, a progressive curriculum first stabilizes low-frequency structures and then introduces high-frequency constraints to recover fine facial and hair details without amplifying spurious responses at early stages.1
• For cross-view optimization, we introduce Canonical Group Consensus, which associates local observations through shared canonical surface regions and establishes correspondence across different viewpoints.1

Sources (1)

• [1]Fresco++: Frequency-Guided and Canonical-Consistent Optimization for Fine-Grained Head Avatar Modeling
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:43 AM

  We propose Fresco++, a unified optimization framework for fine-grained and view-consistent head avatar reconstruction.

  Head avatar optimization is typically driven by per-view image supervision, which can lead to premature fitting of unstable high-frequency details and inconsistent local appearance across viewpoints.

Extractive summary: sentences quoted from the sources.