AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Image Harmonization in the Linear Color Space

Ke Xu, Gerhard Petrus Hancke, Rynson W.H. Lau

ICCV 2023 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 12 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 image unprocessing to convert to linear color space (ablation)color harmonization network · iHarmony4 average (256x256)PSNR: 37.79 -> 39.36Improved
use diffusion process in image unprocessing instead of standard convolution (ablation)image unprocessing · iHarmony4 average (256x256)PSNR: 38.28 -> 39.36Improved
add feature harmonization (bilateral propagation) (ablation)color harmonization · iHarmony4 average (256x256)PSNR: 38.10 -> 39.36Improved
add background preserving guided rendering (ablation)color rendering · iHarmony4 average (256x256)PSNR: 39.17 -> 39.36Improved
use two encoders instead of a single encoder (ablation)color harmonization network · iHarmony4 average (256x256)PSNR: 39.02 -> 39.36Improved
add SE block in feature harmonization (ablation)feature harmonization · iHarmony4 average (256x256)PSNR: 38.47 -> 39.36Improved
add spatial attention in feature harmonization (ablation)feature harmonization · iHarmony4 average (256x256)PSNR: 38.19 -> 39.36Improved
fine-tune pre-trained DoveNet in linear spaceDoveNet · iHarmony4PSNR: 34.75 -> 33.18 (-1.57)Hurt
train DoveNet from scratch in linear spaceDoveNet · iHarmony4PSNR: +0.19 (34.94)No clear effect
use ControlNet diffusion model for harmonizationControlNet · iHarmony4PSNR: PSNR/MAE 14.36/109.40Hurt
learned image unprocessing module vs prior sRGB-to-linear methodsimage unprocessing · Adobe5K CIE XYZPSNR: 29.66 -> 30.34Improved

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