AI Paper Atlas

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

MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis

Dewei Zhou, You Li, Fan Ma, Zongxin Yang, Yi Yang

TPAMI 2024 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 20 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 Enhance Attention (ablation)MIGC · COCO-PositionSuccess Ratio: 34.7 -> 80.2Improved
add Layout Attention to Enhance Attention + SAC (ablation)MIGC · COCO-PositionSuccess Ratio: 80.2 -> 80.3No clear effect
add Shading Aggregation Controller (ablation)MIGC · COCO-PositionSuccess Ratio: 78.1 -> 80.3Improved
add Refined Shader (MIGC++ over MIGC)MIGC · COCO-MIG-BOXInstance Success Ratio: 69.2 -> 71.4Improved
add Refined Shader (MIGC++ over MIGC)MIGC · COCO-PositionSuccess Ratio: 80.29 -> 82.54Improved
deploy Instance Shader in mid and up-1 instead of mid only (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 46.9 -> 71.4Improved
also deploy Instance Shader in up-2 (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 71.4 -> 66.5Hurt
also deploy Instance Shader in down-2 (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 71.4 -> 66.4Hurt
deploy Instance Shader in all blocks (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 71.4 -> 65.7Hurt
control first 50% of sampling steps instead of 30% (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 66.9 -> 71.4Improved
extend control from 50% to 60% of steps (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 71.4 -> 69.8Hurt
deploy Refined Shader in all blocks vs none (ablation)MIGC++ · COCO-MIG-BOXInstance Success Ratio: 67.2 -> 71.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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