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
Abstract
We present SIGMA-GEN, a unified framework for multi-identity preserving image generation. Unlike prior approaches, SIGMA-GEN is the first to enable single-pass multi-subject identity-preserved generation guided by both structural and spatial constraints. A key strength of our method is its ability to support user guidance at various levels of precision — from coarse 2D or 3D boxes to pixel-level segmentations and depth — with a single model. To enable this, we introduce SIGMA-SET27K, a novel synthetic dataset that provides identity, structure, and spatial information for over 100k unique subjects across 27k images. Through extensive evaluation we demonstrate that SIGMA-GEN achieves state-of-the-art performance in identity preservation, image generation quality, and speed.
BibTeX
@inproceedings{
saha2026sigmagen,
title={{SIGMA}-{GEN}: {STRUCTURE} {AND} {IDENTITY} {GUIDED} {MULTI}-{SUBJECT} {ASSEMBLY} {FOR} {IMAGE} {GENERATION}},
author={Oindrila Saha and Vojtech Krs and Radomir Mech and Subhransu Maji and Kevin James Blackburn-Matzen and Matheus Gadelha},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=x2DWTywZ1i}
}