{"ID":2859601,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06469","arxiv_id":"2510.06469","title":"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. Code and visualizations at https://oindrilasaha.github.io/SIGMA-Gen/","short_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 guida...","url_abs":"https://arxiv.org/abs/2510.06469","url_pdf":"https://arxiv.org/pdf/2510.06469v1","authors":"[\"Oindrila Saha\",\"Vojtech Krs\",\"Radomir Mech\",\"Subhransu Maji\",\"Kevin Blackburn-Matzen\",\"Matheus Gadelha\"]","published":"2025-10-07T21:12:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}