SIGMA-Gen: Structure and Identity Guided Multi-Subject Assembly for Image Generation

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.

Cite

Text

Saha et al. "SIGMA-Gen: Structure and Identity Guided Multi-Subject Assembly for Image Generation." International Conference on Learning Representations, 2026.

Markdown

[Saha et al. "SIGMA-Gen: Structure and Identity Guided Multi-Subject Assembly for Image Generation." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/saha2026iclr-sigmagen/)

BibTeX

@inproceedings{saha2026iclr-sigmagen,
  title     = {{SIGMA-Gen: Structure and Identity Guided Multi-Subject Assembly for Image Generation}},
  author    = {Saha, Oindrila and Krs, Vojtech and Mech, Radomir and Maji, Subhransu and Blackburn-Matzen, Kevin James and Gadelha, Matheus},
  booktitle = {International Conference on Learning Representations},
  year      = {2026},
  url       = {https://mlanthology.org/iclr/2026/saha2026iclr-sigmagen/}
}