AI Paper Atlas

Research map / Image generation / Editing and style transfer

SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing

Jing Shi, Ning Xu, Haitian Zheng, Alex Smith, Jiebo Luo, Chenliang Xu

CVPR 2022 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 16 citations (OpenAlex)

Check 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 the unified multimodal editing generator instead of BiCycleGAN or DivCoopen-domain image editing on Discover · Discover testFID and LPIPS: FID: 9.9586 -> 5.1755; LPIPS: 0.1705 -> 0.1945 (DivCo); FID: 12.2837 -> 5.1755; LPIPS: 0.0857 -> 0.1945 (BiCycleGAN)Improved
use the pretrained editing generator and predict an editing latent from image and languagesupervised LGIE · MA5k-Req testL1, SSIM, and FID: L1: 0.0784 -> 0.0731; SSIM: 0.8459 -> 0.8721; FID: 6.7571 -> 5.9791Improved
use cosine distance instead of euclidean distance for clustering latent editing codesW-space editing-style clustering · Discover datasetPurity: 11.30 -> 12.76Improved
cluster editing styles in W space rather than Lightroom operation spaceediting-style clustering · Discover datasetPurity: 4.25 -> 12.76Improved
remove deeper encoder and decoder layers (ablation)multimodal editing generator · Discover testFID: 5.1755 -> 6.0958Hurt
remove deeper encoder and decoder layers (ablation)multimodal editing generator · Discover testLPIPS: 0.1945 -> 0.1581Hurt
co-modulate the decoder with input-image features (ablation)multimodal editing generator · Discover testFID: 5.1755 -> 5.6355Hurt
co-modulate the decoder with input-image features (ablation)multimodal editing generator · Discover testLPIPS: 0.1945 -> 0.1479Hurt
remove visual input when predicting the editing latent (ablation)supervised LGIE · MA5k-Req testL1, SSIM, and FID: L1: 0.0731 -> 0.0795; SSIM: 0.8721 -> 0.8596; FID: 5.9791 -> 6.9757Hurt
remove visual input when predicting the editing latent (ablation)supervised LGIE · MA5k-Req testimage variance (σ×10²): 0.6809 -> 0.6281Hurt

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