AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Trace Controlled Text to Image Generation

Kun Yan, Lei Ji, Chenfei Wu, Jianmin Bao, Ming Zhou, Nan Duan, Shuai Ma

ECCV 2022 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 10 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 mouse trace input (ablation)TCTIG text-only · LN-COCO val (GAN synthesis ablation)SSCP: 0.727 -> 0.923Improved
add mouse trace input (ablation)TCTIG text-only · LN-COCO val (GAN synthesis ablation)FID: 75.34 -> 29.58Improved
add segment aligned augmentation (SAA) (ablation)TCTIG (-TGR) · LN-COCO val (GAN synthesis ablation)FID: 29.58 -> 26.50Improved
add segment aligned augmentation (SAA) (ablation)TCTIG (-TGR) · LN-COCO val (GAN synthesis ablation)SOA-I: 0.1320 -> 0.2200Improved
add segment aligned augmentation (SAA) (ablation)TCTIG (-TGR) · LN-COCO val (GAN synthesis ablation)SSCP: 0.923 -> 0.955Improved
add trace guided re-weighting loss (TGR) (ablation)TCTIG · LN-COCO val (GAN synthesis ablation)FID: 26.50 -> 19.54Improved
add trace guided re-weighting loss (TGR) (ablation)TCTIG · LN-COCO val (GAN synthesis ablation)SSCP: 0.955 -> 0.962Improved
replace GAN-based VQGAN decoder with VQ-conditioned diffusion decoder (ablation)TCTIG · LN-COCO val (GAN synthesis ablation)FID: 19.54 -> 11.94Improved
replace GAN-based VQGAN decoder with VQ-conditioned diffusion decoder (ablation)TCTIG · LN-COCO val (GAN synthesis ablation)SSCP: 0.962 -> 0.973Improved
replace GAN decoder with diffusion decoder on ground truth tokens (ablation)GT image reconstruction · LN-COCO val (GAN synthesis ablation)FID: 12.74 -> 8.62Improved
use TCTIG instead of TRECStrace-controlled generation · LN-COCO valSSCP: 0.862 -> 0.973Improved
use TCTIG instead of TRECStrace-controlled generation · LN-COCO valSOA-I: 0.3523 -> 0.2658Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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