AI Paper Atlas

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

SIGMA-GEN: STRUCTURE AND IDENTITY GUIDED MULTI-SUBJECT ASSEMBLY FOR IMAGE GENERATION

Oindrila Saha, Vojtech Krs, Radomir Mech, Subhransu Maji, Kevin James Blackburn-Matzen, Matheus Gadelha

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 3 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 SIGMA-Gen single-pass multi-subject generation instead of iterative Insert Anything*multi-subject generation, mask+depth · SIGMA-Set27K multi subjectDINO-I: 72.72 -> 74.54Improved
Use SIGMA-Gen instead of Insert Anything*multi-subject generation, mask+depth · SIGMA-Set27K multi subjectCLIP-IQA: 44.41 -> 72.64Improved
Use SIGMA-Gen instead of Insert Anything*multi-subject generation, mask+depth · SIGMA-Set27K multi subjectDepth MSE: 203.4 -> 26.35Improved
Use SIGMA-Gen instead of MSDiffusion for bbox controlmulti-subject generation, bbox · SIGMA-Set27K multi subjectDINO-I: 63.28 -> 71.90Improved
Use SIGMA-Gen instead of MSDiffusion for bbox controlsingle-subject generation, bbox · SIGMA-Set27K single subjectDINO-I: 74.83 -> 79.16Improved
Use SIGMA-Gen instead of Flux Kontext* (depth ControlNet)single-subject generation, mask+depth · SIGMA-Set27K single subjectDINO-I: 79.96 -> 81.04Improved
Use SIGMA-Gen instead of Insert Anything* on text alignmentsingle-subject generation, mask+depth · SIGMA-Set27K single subjectSigLIP-T: 16.01 -> 15.91Hurt
Use SIGMA-Gen instead of UniCombine on image qualitysingle-subject generation, mask+depth · SIGMA-Set27K single subjectCLIP-IQA: 71.47 -> 70.65Hurt
Provide full depth instead of subject-only depth at inference (ablation)SIGMA-Gen · SIGMA-Set27K ablationsubject consistency and other scoresMixed
Use full scene prompt instead of background-only prompt (ablation)SIGMA-Gen mask+depth · SIGMA-Set27K ablationall metricsImproved
Add depth to precise masks (ablation)SIGMA-Gen · SIGMA-Set27K ablationall metricsImproved
Feed depth via structure control image rather than external depth ControlNet (ablation)SIGMA-Gen · SIGMA-Set27K ablationconsistency, text alignment, qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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