AI Paper Atlas

Research map / Video / Video segmentation and tracking

Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement

Lingyu Zhu, Wenhan Yang, Baoliang Chen, Hanwei Zhu, Zhangkai Ni, Qi Mao, Shiqi Wang

ECCV 2024 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 13 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 temporal subnet (b) to stage-1 illumination subnet (ablation)UDU-Net · SDSD outdoorwarp error: 0.54 -> 0.20Improved
add temporal subnet (b) to stage-1 illumination subnet (ablation)UDU-Net · SDSD outdoorPSNR: 21.29 -> 21.43Improved
add second-stage illumination subnet (c) (ablation)UDU-Net · SDSD outdoorPSNR: 21.43 -> 23.92 PSNR; warp 0.20 -> 0.35Mixed
add human perception feedback (BRISQUE-selected targets) in stage 2 (ablation)UDU-Net · SDSD outdoorPSNR: 21.87 -> 23.94Improved
add human perception feedback (ablation)UDU-Net · SDSD outdoorwarp error: 0.14 -> 0.24Hurt
add human perception feedback (ablation)UDU-Net · SDSD indoorPSNR: 22.00 -> 22.41Improved
reference-free UDU-Net vs second-best reference-free methodUDU-Net · SDSD outdoorPSNR: gain of 2.05 dB and 0.1158 SSIMImproved
reference-free UDU-Net vs supervised SDSDNetUDU-Net · SDSD indoorPSNR: 27.03 vs 22.41Hurt

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