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)→
More from Research
- LagTag Chromatin Recording Work Formally Published — arjunrajlab · 2026-09-03
- SIGGRAPH Asia 2026 travel grant applications open, due September 18 — tomaszbednarz · 2026-09-03
- Planted 100 errors in papers to test AI peer review: best system caught 71, ensembles 93 — alejandroll10 · 2026-09-03
- EMNLP paper: pretraining on romanized text beats raw text for cross-lingual transfer — TuhinChakr · 2026-09-03
- HydroGym RL platform for fluid dynamics published in Nature with 60+ environments — ricardovinuesa · 2026-09-03
- Paper proposes agents that outlive their model, harness, and host by splitting identity from plumbing — omarsar0 · 2026-09-03