Trained Vision Models Remove Rolling Shutter Artifacts and Recover Depth

Developers show that trained vision models can remove rolling shutter artifacts, which can also help recover camera state information and serve as heuristic features for monocular depth restoration, though the technique has limitations.

2026-09-01 ~ 2026-09-01 · 2 related posts

• Training Vision Models to Undo Rolling Shutter Artifacts — astridwilde1 · 2026-09-01
• Vision models can undo rolling shutter artifacts and recover camera state — yacineMTB · 2026-09-01