SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saha, Oindrila, Krs, Vojtech, Mech, Radomir, Maji, Subhransu, Blackburn-Matzen, Kevin, Gadelha, Matheus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909830893010944
author Saha, Oindrila
Krs, Vojtech
Mech, Radomir
Maji, Subhransu
Blackburn-Matzen, Kevin
Gadelha, Matheus
author_facet Saha, Oindrila
Krs, Vojtech
Mech, Radomir
Maji, Subhransu
Blackburn-Matzen, Kevin
Gadelha, Matheus
contents 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. Code and visualizations at https://oindrilasaha.github.io/SIGMA-Gen/
format Preprint
id arxiv_https___arxiv_org_abs_2510_06469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation
Saha, Oindrila
Krs, Vojtech
Mech, Radomir
Maji, Subhransu
Blackburn-Matzen, Kevin
Gadelha, Matheus
Computer Vision and Pattern Recognition
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. Code and visualizations at https://oindrilasaha.github.io/SIGMA-Gen/
title SIGMA-GEN: Structure and Identity Guided Multi-subject Assembly for Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.06469