AI Paper Atlas

Research map / Image generation / Image restoration

Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization

Jingtang Liang, Xiaodong Cun, Chi-Man Pun, Jue Wang

ECCV 2022 · Image generation › Image restoration · approach: Image harmonization and color transformation · 43 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
use relative L1 loss on the masked region instead of plain L1 (ablation)S2CRNet-SqueezeNet · iHarmony4 PSNRPSNR: 32.11 -> 36.20Improved
add adversarial loss (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 36.20 -> 36.27Improved
add adversarial loss (ablation)S2CRNet-SqueezeNet · HCOCOPSNR: 37.59 -> 37.51No clear effect
use spatial-separated encoder instead of foreground-only features (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 34.57 -> 36.27Improved
use spatial-separated encoder instead of full-image features (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 33.88 -> 36.27Improved
add cascaded refinement to CRM (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 36.27 -> 36.41Improved
add semantic labels to cascaded CRM (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 36.41 -> 36.45Improved
use piece-wise linear curve instead of Zero-DCE curve (ablation)CRM · iHarmony4PSNR: 34.39 -> 36.27Improved
use piece-wise linear curve instead of 3DLUT (ablation)CRM · iHarmony4PSNR: 35.49 -> 36.27Improved
set curve levels L=64 instead of 32 (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 36.17 -> 36.45Improved
increase curve levels L from 64 to 128 (ablation)S2CRNet-SqueezeNet · iHarmony4PSNR: 36.45 -> 36.19Hurt
use VGG16 backbone instead of SqueezeNetS2CRNet · iHarmony4PSNR: 36.45 -> 37.18Improved

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