AI Paper Atlas

Research map / Video / Video segmentation and tracking

Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos

Shreshth Saini, Bowen Chen, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik

CVPR 2026 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add HDR-aware encoder fine-tuning to GRPO (ablation)GRPO baseline · Beyond8Bits ablationSRCC: 0.81 -> 0.83Improved
add HDR-aware encoder fine-tuning to GRPO (ablation)GRPO baseline · Beyond8Bits ablationRMSE: 10.73 -> 8.96Improved
add HAPO, HDR-SDR KL, dual entropy, HEW and self-reward on top of HDR encoder (ablation)GRPO + HDR-Enc. · Beyond8Bits ablationSRCC: 0.83 -> 0.92Improved
add HDR-SDR contrastive KL (ablation)HDR-Q · Beyond8Bits ablationSRCC: 0.86 -> 0.92Improved
add HDR-SDR contrastive KL (ablation)HDR-Q · Beyond8Bits ablationRMSE: 7.10 -> 5.15Improved
add dual entropy regularization (ablation)HDR-Q · Beyond8Bits ablationSRCC: 0.91 -> 0.92No clear effect
add dual entropy regularization (ablation)HDR-Q · Beyond8Bits ablationRMSE: 5.82 -> 5.15Improved
add entropy-weighted credit assignment (HEW) (ablation)HDR-Q · Beyond8Bits ablationSRCC: 0.88 -> 0.92Improved
add entropy-weighted credit assignment (HEW) (ablation)HDR-Q · Beyond8Bits ablationRMSE: 6.11 -> 5.15Improved
add self-reward (ablation)HDR-Q · Beyond8Bits ablationSRCC: 0.92 -> 0.92No clear effect
add self-reward (ablation)HDR-Q · Beyond8Bits ablationPLCC: 0.90 -> 0.91Improved
feed 10-bit HDR input rather than SDR-only input (ablation)HDR-Q · Beyond8Bits (test)SRCC: 0.8914 -> 0.9206Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy