mlsanityData to 14 Oct 2026

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

arXiv 2510.06469 ↗First posted 7 Oct 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

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/

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 50 of its 54 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

50 of 54 references.

References · 50

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2022Flow Matching for Generative Modelingcited by 5,702
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  8. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  11. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  12. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
38 more
  1. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  2. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  3. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  4. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  5. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  6. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  7. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  8. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  9. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  10. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  11. 2023BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editingcited by 442
  12. 2023ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generationcited by 416
  13. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 412
  14. 2024OmniGen: Unified Image Generationcited by 394
  15. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 340
  16. 2021VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalizationcited by 287
  17. 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Modelscited by 261
  18. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
  19. 2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generationcited by 259
  20. 2024InstanceDiffusion: Instance-level Control for Image Generationcited by 175
  21. 2025Less-to-More Generalization: Unlocking More Controllability by In-Context Generationcited by 154
  22. 2023Cones: Concept Neurons in Diffusion Models for Customized Generationcited by 150
  23. 2024MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidancecited by 144
  24. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 133
  25. 2023Cones 2: Customizable Image Synthesis with Multiple Subjectscited by 101
  26. 2025DreamO: A Unified Framework for Image Customizationcited by 83
  27. 2023LooseControl: Lifting ControlNet for Generalized Depth Conditioningcited by 68
  28. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  29. 2023GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generationcited by 56
  30. 2025XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulationcited by 56
  31. 2024MultiBooth: Towards Generating All Your Concepts in an Image from Textcited by 45
  32. 2024Identity Decoupling for Multi-Subject Personalization of Text-to-Image Modelscited by 33
  33. 2025UniCombine: Unified Multi-Conditional Combination with Diffusion Transformercited by 26
  34. 2023Generating Images with 3D Annotations Using Diffusion Modelscited by 18
  35. 2025MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routingcited by 11
  36. 2025Multitwine: Multi-Object Compositing with Text and Layout Controlcited by 9
  37. 2024Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generationcited by 8
  38. 2025Controllable 3D Placement of Objects with Scene-Aware Diffusion Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026LooseControlVideo: Directorial Video Control using Spatial Blockingcited by 2
  2. 20263D Space as a Scratchpad for Editable Text-to-Image Generationcited by 1
  3. 2026MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editingcited by 1
  4. 2026Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generationcited by 0
  5. 2026Appearance Pointers -- Multimodal Region Control of Diffusion Transformerscited by 0