research
Pairwise Image Judgments Guided the Motion Repair
A learned comparator ranked same-target reconstructions so derivative-free search could reduce motion artifacts without an absolute quality score.
Summary
A learned comparator ranked same-target reconstructions so derivative-free search could reduce motion artifacts without an absolute quality score.
Deep preferential evolution learned relative image quality in simulation, then used unlabeled domain calibration for in-vivo photoacoustic tomography. The authors report correction of synthetic motion and mitigation of natural motion artifacts in human-palm imaging.
Why it matters
A learned comparator ranked same-target reconstructions so derivative-free search could reduce motion artifacts without an absolute quality score.
Limits and context
No additional limitation was separately recorded.
Key claims
A learned comparator ranked same-target reconstructions so derivative-free search could reduce motion artifacts without an absolute quality score.
Evidence: source-2026-10-11-020
Sources
- arXiv preprint 2610.12273, original v1arXiv / submitting research authors · primary research
Corrections
No corrections have been recorded for this story.