ComposeAnything: Composite Object Priors for Text-to-Image Generation

• URL: http://arxiv.org/abs/2505.24086v1
• Date: Fri, 30 May 2025 00:13:36 GMT
• Title: ComposeAnything: Composite Object Priors for Text-to-Image Generation
• Authors: Zeeshan Khan, Shizhe Chen, Cordelia Schmid,
• Abstract summary: ComposeAnything is a novel framework for improving compositional image generation without retraining existing T2I models.<n>Our approach first leverages the chain-of-thought reasoning abilities of LLMs to produce 2.5D semantic layouts from text.<n>Our model generates high-quality images with compositions that faithfully reflect the text.
• Score: 72.98469853839246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating images from text involving complex and novel object arrangements remains a significant challenge for current text-to-image (T2I) models. Although prior layout-based methods improve object arrangements using spatial constraints with 2D layouts, they often struggle to capture 3D positioning and sacrifice quality and coherence. In this work, we introduce ComposeAnything, a novel framework for improving compositional image generation without retraining existing T2I models. Our approach first leverages the chain-of-thought reasoning abilities of LLMs to produce 2.5D semantic layouts from text, consisting of 2D object bounding boxes enriched with depth information and detailed captions. Based on this layout, we generate a spatial and depth aware coarse composite of objects that captures the intended composition, serving as a strong and interpretable prior that replaces stochastic noise initialization in diffusion-based T2I models. This prior guides the denoising process through object prior reinforcement and spatial-controlled denoising, enabling seamless generation of compositional objects and coherent backgrounds, while allowing refinement of inaccurate priors. ComposeAnything outperforms state-of-the-art methods on the T2I-CompBench and NSR-1K benchmarks for prompts with 2D/3D spatial arrangements, high object counts, and surreal compositions. Human evaluations further demonstrate that our model generates high-quality images with compositions that faithfully reflect the text.

Related papers

• Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models [3.5999252362400993]
  A prevalent issue in compositional generation is the misalignment of spatial relationships.<n>We introduce a novel evaluation metric designed to assess the alignment of 2D and 3D spatial relationships between text and image.<n>We also propose PoS-based Generation, an inference-time method that improves the alignment of 2D and 3D spatial relationships in T2I models without requiring fine-tuning.
  arXiv  Detail & Related papers  (2025-06-29T22:41:27Z)
• CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback [58.27353205269664]
  State-of-the-art T2I models are capable of generating high-resolution images given textual prompts.<n>However, they struggle with accurately depicting compositional scenes that specify multiple objects, attributes, and spatial relations.<n>We present CompAlign, a challenging benchmark with an emphasis on assessing the depiction of 3D-spatial relationships.
  arXiv  Detail & Related papers  (2025-05-16T12:23:58Z)
• BIFRÖST: 3D-Aware Image compositing with Language Instructions [27.484947109237964]
  Bifr"ost is a novel 3D-aware framework that is built upon diffusion models to perform instruction-based image composition. Bifr"ost addresses issues by training MLLM as a 2.5D location predictor and integrating depth maps as an extra condition during the generation process.
  arXiv  Detail & Related papers  (2024-10-24T18:35:12Z)
• SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing [58.22339174221563]
  We propose SyncNoise, a novel geometry-guided multi-view consistent noise editing approach for high-fidelity 3D scene editing. SyncNoise synchronously edits multiple views with 2D diffusion models while enforcing multi-view noise predictions to be geometrically consistent. Our method achieves high-quality 3D editing results respecting the textual instructions, especially in scenes with complex textures.
  arXiv  Detail & Related papers  (2024-06-25T09:17:35Z)
• TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation [21.171612603385405]
  We present TextCenGen, a training-free dynamic background adaptation in the blank region for text-friendly image generation.<n>Our method analyzes cross-attention maps to identify conflicting objects overlapping with text regions and uses a force-directed graph approach to guide their relocation.<n>Our method is plug-and-play, requiring no additional training while well balancing both semantic fidelity and visual quality.
  arXiv  Detail & Related papers  (2024-04-18T01:10:24Z)
• DivCon: Divide and Conquer for Progressive Text-to-Image Generation [0.0]
  Diffusion-driven text-to-image (T2I) generation has achieved remarkable advancements. layout is employed as an intermedium to bridge large language models and layout-based diffusion models. We introduce a divide-and-conquer approach which decouples the T2I generation task into simple subtasks.
  arXiv  Detail & Related papers  (2024-03-11T03:24:44Z)
• TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes [67.5351491691866]
  We present a novel framework, dubbed TeMO, to parse multi-object 3D scenes and edit their styles. Our method can synthesize high-quality stylized content and outperform the existing methods over a wide range of multi-object 3D meshes.
  arXiv  Detail & Related papers  (2023-12-07T12:10:05Z)
• X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation [61.48050470095969]
  X-Dreamer is a novel approach for high-quality text-to-3D content creation. It bridges the gap between text-to-2D and text-to-3D synthesis.
  arXiv  Detail & Related papers  (2023-11-30T07:23:00Z)
• Vox-E: Text-guided Voxel Editing of 3D Objects [14.88446525549421]
  Large scale text-guided diffusion models have garnered significant attention due to their ability to synthesize diverse images. We present a technique that harnesses the power of latent diffusion models for editing existing 3D objects.
  arXiv  Detail & Related papers  (2023-03-21T17:36:36Z)
• Towards Realistic 3D Embedding via View Alignment [53.89445873577063]
  This paper presents an innovative View Alignment GAN (VA-GAN) that composes new images by embedding 3D models into 2D background images realistically and automatically. VA-GAN consists of a texture generator and a differential discriminator that are inter-connected and end-to-end trainable.
  arXiv  Detail & Related papers  (2020-07-14T14:45:00Z)

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.