AI Paper Atlas

Research map / Image generation / Image restoration

Ultra-High-Definition Image HDR Reconstruction via Collaborative Bilateral Learning

Zhuoran Zheng, Wenqi Ren, Xiaochun Cao, Tao Wang, Xiuyi Jia

ICCV 2021 · Image generation › Image restoration · approach: Image harmonization and color transformation · 41 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 3D Tucker reconstruction of bilateral grids (ablation)Ours · M-exposure (ablation)PSNR (dB): 20.81 -> 23.29Improved
use 3D Tucker instead of 1D Tucker (ablation)Ours · M-exposure (ablation)PSNR (dB): 20.35 -> 23.29Improved
add self-evolving loss (ablation)Ours · M-exposure (ablation)PSNR (dB): 22.03 -> 23.29Improved
add color stream and LeakyAdaIN (dual path vs single path) (ablation)Ours · M-exposure (ablation)PSNR (dB): 19.97 -> 23.29Improved
add 3D Tucker reconstruction of bilateral grids (ablation)Ours · M-exposure (ablation)Q-Score: 42.89 -> 46.68Improved
add color stream and LeakyAdaIN (dual path vs single path) (ablation)Ours · M-exposure (ablation)SSIM: 0.58 -> 0.7702Improved
use gray image instead of low-res color as content-stream input (ablation)Ours · UHD test imagesvisual qualityImproved
use downsample-enhancement-upsample instead of split-stitch for baselines (ablation)baseline HDR methods · UHD test dataPSNR/SSIMImproved

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