Skip to main content
Search

# Hybrid OLAT-Gen Training Data

1 related articles

Subscribe to updates
  1. arXiv

    Portrait video relighting stops assuming static light: FlashRelight splits delighting from relighting to follow frame-by-frame envmap sequences

    Portrait video relighting has mostly targeted static or mildly varying illumination, and struggles when direction, intensity and color change over time. FlashRelight splits the task in two: a delighting model suppresses the source lighting to obtain an approximately illumination-neutral video, then a relighting model built on a DiT video generative prior synthesizes the target dynamic lighting. It accepts environment-map sequences, dynamic lighting text and lighting reference videos as controls; on a held-out test set of 10 subjects and 16 envmap sequences it beats the three listed baselines on lighting accuracy, LPIPS, identity similarity, PSNR and tLPIPS.

You’re all caught up