Vision models can undo rolling shutter artifacts and recover camera state

yacineMTB · x · 2026-09-01

Discussion suggests that vision models can be trained to remove rolling shutter artifacts. These artifacts are actually useful for recovering camera state information and serve as heuristics for many monocular depth recovery models, though public research on this is currently scarce.

Related event: Trained Vision Models Remove Rolling Shutter Artifacts and Recover Depth(2 posts)→

Original post →

More from Research

Research channel →