MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics

• URL: http://arxiv.org/abs/2603.21136v1
• Date: Sun, 22 Mar 2026 09:15:21 GMT
• Title: MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics
• Abstract summary: We introduce MS-CustomNet, a novel framework for multi-subject customization.<n>MS-CustomNet allows zero-shot integration of multiple user-provided objects.<n>Our method achieves a DINO-I score of 0.61 for identity preservation and a YOLO-L score of 0.94 for positional control in multi-subject customization tasks.
• Score: 4.05356944557183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with multiple distinct subjects while maintaining fine-grained control over their interactions remains challenging. Existing methods often struggle to provide explicit user-defined control over the compositional structure and precise spatial relationships between subjects. To address this, we introduce MS-CustomNet, a novel framework for multi-subject customization. MS-CustomNet allows zero-shot integration of multiple user-provided objects and, crucially, empowers users to explicitly define these hierarchical arrangements and spatial placements within the generated image. Our approach ensures individual subject identity preservation while learning and enacting these user-specified inter-subject compositions. We also present the MSI dataset, derived from COCO, to facilitate training on such complex multi-subject compositions. MS-CustomNet offers enhanced, fine-grained control over multi-subject image generation. Our method achieves a DINO-I score of 0.61 for identity preservation and a YOLO-L score of 0.94 for positional control in multi-subject customization tasks, demonstrating its superior capability in generating high-fidelity images with precise, user-directed multi-subject compositions and spatial control.

Related papers

• MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding [9.605365111072745]
  MultiCompose is a composition framework that decouples per-concept personalization from multi-subject inference.<n>MSP-Bench is a benchmark that jointly evaluates identity fidelity (ID), attribute binding accuracy (BIND), and attribute misalignment (MIS)<n>Experiments show that MultiCompose outperforms existing methods on both conventional metrics and MSP-Bench.
  arXiv  Detail & Related papers  (2026-08-04T14:13:18Z)
• Unified Personalized Understanding, Generating and Editing [54.5563878110386]
  We present textbf OmniPersona, an end-to-end personalization framework for unified LMMs.<n>It integrates personalized understanding, generation, and image editing within a single architecture.<n>Experiments demonstrate that OmniPersona delivers competitive and robust performance across diverse personalization tasks.
  arXiv  Detail & Related papers  (2026-01-11T15:46:34Z)
• MoGen: A Unified Collaborative Framework for Controllable Multi-Object Image Generation [76.94658056824422]
  MoGen is a user-friendly multi-object image generation method.<n>First, we design a Regional Semantic Anchor (RSA) module that precisely anchors phrase units in language descriptions to their corresponding image regions.<n>We introduce an Adaptive Multi-modal Guidance (AMG) module, which adaptively parses and integrates various combinations of multi-source control signals.
  arXiv  Detail & Related papers  (2026-01-09T05:57:48Z)
• AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization [55.06425570300248]
  We present AnyMS, a training-free framework for layout-guided multi-subject customization.<n>AnyMS leverages three input conditions: text prompt, subject images, and layout constraints.<n>AnyMS achieves state-of-the-art performance, supporting complex compositions and scaling to a larger number of subjects.
  arXiv  Detail & Related papers  (2025-12-29T15:26:25Z)
• Canvas-to-Image: Compositional Image Generation with Multimodal Controls [51.44122945214702]
  We introduce Canvas-to-Image, a unified framework that consolidates heterogeneous controls into a single canvas interface.<n>Our key idea is to encode diverse control signals into a single composite canvas image that the model can interpret for integrated visual-spatial reasoning.
  arXiv  Detail & Related papers  (2025-11-26T18:59:56Z)
• ConsistCompose: Unified Multimodal Layout Control for Image Composition [56.909072845166264]
  We present ConsistCompose, a unified framework that embeds layout coordinates directly into language prompts.<n>We show that ConsistCompose substantially improves spatial accuracy over layout-controlled baselines.
  arXiv  Detail & Related papers  (2025-11-23T08:14:53Z)
• MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion [24.513096225720854]
  We introduce a novel task, multi-view customization, which aims to jointly achieve multi-view pose control and customization.<n>We propose MVCustom, a novel diffusion-based framework explicitly designed to achieve both multi-view consistency and customization fidelity.
  arXiv  Detail & Related papers  (2025-10-15T16:00:26Z)
• ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation [24.487453636504707]
  We introduce ContextGen, a novel Diffusion Transformer framework for multi-instance generation.<n>We show that ContextGen sets a new state-of-the-art, outperforming existing methods in control precision, identity fidelity, and overall visual quality.
  arXiv  Detail & Related papers  (2025-10-13T04:21:19Z)
• UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward [15.094319754425468]
  We present UMO, a framework designed to maintain high-fidelity identity preservation and alleviate identity confusion with scalability.<n>With "multi-to-multi matching" paradigm, UMO reformulates multi-identity generation as a global assignment optimization problem.<n>We develop a scalable customization dataset with multi-reference images, consisting of both synthesised and real parts.
  arXiv  Detail & Related papers  (2025-09-08T15:54:55Z)
• CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models [85.69959024572363]
  CustomNet is a novel object customization approach that explicitly incorporates 3D novel view synthesis capabilities into the object customization process. We introduce delicate designs to enable location control and flexible background control through textual descriptions or specific user-defined images. Our method facilitates zero-shot object customization without test-time optimization, offering simultaneous control over the viewpoints, location, and background.
  arXiv  Detail & Related papers  (2023-10-30T17:50:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.