Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares

The paper introduces Semi-LAR, a semi‑supervised framework for removing nighttime lens flares. It uses an adaptive pseudo‑label repository that refines supervision through quality assessment, momentum updates, and invalid label filtering. A flare‑aware contrastive loss treats flare‑contaminated inputs as negatives, encouraging representations that distinguish flare patterns while aligning with reliable pseudo targets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• benchmarks