AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Towards Real-World HDRTV Reconstruction: A Data Synthesis-Based Approach

Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, Chang Chen, Zhiwei Xiong

ECCV 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 9 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 HTMP content loss to adversarial loss (ablation)data synthesis network · RealHDRTV synthesisPSNR: 11.74 -> 24.54Improved
add adversarial loss to HTMP loss (ablation)data synthesis network · RealHDRTV synthesisPSNR: 24.24 -> 24.54Improved
use region-aware HTMP loss instead of L1 to Linear TMO (ablation)data synthesis network · RealHDRTV synthesisPSNR: 16.35 -> 24.54Improved
use region-aware HTMP loss instead of L1 to mu-law TMO (ablation)data synthesis network · RealHDRTV synthesisPSNR: 18.18 -> 24.54Improved
use region-aware HTMP loss instead of L1 to Youtube TMO (ablation)data synthesis network · RealHDRTV synthesisPSNR: 23.32 -> 24.54Improved
add condition network with tone mapping results (ablation)data synthesis network · RealHDRTV synthesisPSNR: 24.08 -> 24.54Improved
condition on prior TMO results instead of the input HDRTV itself (ablation)data synthesis network · RealHDRTV synthesisPSNR: 24.15 -> 24.54Improved
add local adjustment stream to global stream (ablation)data synthesis network · RealHDRTV synthesisPSNR: 24.33 -> 24.54Improved
add global mapping stream to local stream (ablation)data synthesis network · RealHDRTV synthesisPSNR: 24.44 -> 24.54Improved
train HDRTVNet-AGCM on data synthesized by learned method instead of HableHDRTVNet-AGCM · RealHDRTV reconstructionPSNR: 25.44 -> 28.04Improved
synthesize SDRTV with learned method instead of HableSDRTV synthesis · RealHDRTV synthesisPSNR: 23.27 -> 24.54Improved
use TMOs with high TMQI (Rank) for synthesisTMO synthesis · RealHDRTV synthesisPSNR: 22.99 -> 16.57Hurt

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