This PEFT adapter is one result from the BrightRate-LM controlled input and scaling study.
Eight uniformly sampled frames are each rendered at -2, 0, and +2 stops. The 24 images are passed in temporal-major order.
This adapter was trained on the content-separated split 0 of BrightVQ. Training uses two epochs, a three-epoch cosine schedule horizon, learning rate 1e-4, micro-batch 1, gradient accumulation 8, and rank-16 LoRA with alpha 32 and dropout 0.05. MOS targets are interpolated across five quality words.
On the 420-video split-0 test set: SROCC 0.6985, PLCC 0.7297, KRCC 0.5086, RMSE 9.1756.
This adapter is intended for research on no-reference perceptual quality assessment of user-generated HDR video. Scores are not calibrated for other datasets, display pipelines, or video domains.
Code and input construction are available in
BrightRate-LM.
1@article{saini2026brightratelm,
2 title = {BrightRate-LM: Representation-Aware Quality Assessment for User-Generated HDR Video},
3 author = {Saini, Shreshth and Wang, Yilin and Birkbeck, Neil and Adsumilli, Balu and Bovik, Alan C.},
4 journal = {Machine Vision and Applications},
5 year = {2026},
6 note = {Submitted}
7}
