OSInsert: Towards High-authenticity and High-fidelity Image Composition

• URL: http://arxiv.org/abs/2602.19523v1
• Date: Mon, 23 Feb 2026 05:25:05 GMT
• Title: OSInsert: Towards High-authenticity and High-fidelity Image Composition
• Abstract summary: Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image.<n>Some high-authenticity methods can adjust foreground pose/view to be compatible with background, while some high-fidelity methods can preserve the foreground details accurately.<n>In this work, we propose a two-stage strategy to achieve both goals.
• Score: 31.954036253909255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image. Some high-authenticity methods can adjust foreground pose/view to be compatible with background, while some high-fidelity methods can preserve the foreground details accurately. However, existing methods can hardly achieve both goals at the same time. In this work, we propose a two-stage strategy to achieve both goals. In the first stage, we use high-authenticity method to generate reasonable foreground shape, serving as the condition of high-fidelity method in the second stage. The experiments on MureCOM dataset verify the effectiveness of our two-stage strategy. The code and model have been released at https://github.com/bcmi/OSInsert-Image-Composition.

Related papers

• Foreground Focus: Enhancing Coherence and Fidelity in Camouflaged Image Generation [28.86420429221175]
  We propose a Foreground-Aware Camouflaged Image Generation (FACIG) model to generate camouflaged images.<n> Specifically, we introduce a Foreground-Aware Feature Integration Module (FAFIM) to strengthen the integration between foreground features and background knowledge.<n> Experiments on various datasets show our method outperforms previous methods in overall camouflaged image quality and foreground fidelity.
  arXiv  Detail & Related papers  (2025-04-02T23:51:13Z)
• MureObjectStitch: Multi-reference Image Composition [23.110826295932554]
  Generative image composition aims to regenerate the given foreground object in the background image to produce a realistic composite image.<n>The existing methods are struggling to preserve the foreground details and adjust the foreground pose/viewpoint at the same time.<n>We propose an effective finetuning strategy for generative image composition model, in which we finetune a pretrained model using one or more images containing the same foreground object.
  arXiv  Detail & Related papers  (2024-11-12T00:53:20Z)
• Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models [67.68871360210208]
  Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency.<n>We propose a novel fine-tuning objective, dubbed Direct Consistency Optimization, which controls the deviation between fine-tuning and pretrained models.<n>We show that our approach achieves better prompt fidelity and subject fidelity than those post-optimized for merging regular fine-tuned models.
  arXiv  Detail & Related papers  (2024-02-19T09:52:41Z)
• ControlCom: Controllable Image Composition using Diffusion Model [45.48263800282992]
  We propose a controllable image composition method that unifies four tasks in one diffusion model. We also propose a local enhancement module to enhance the foreground details in the diffusion model. The proposed method is evaluated on both public benchmark and real-world data.
  arXiv  Detail & Related papers  (2023-08-19T14:56:44Z)
• LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation [121.45667242282721]
  We propose a coarse-to-fine paradigm to achieve layout planning and image generation. Our proposed method outperforms the state-of-the-art models in terms of photorealistic layout and image generation.
  arXiv  Detail & Related papers  (2023-08-09T17:45:04Z)
• SceneComposer: Any-Level Semantic Image Synthesis [80.55876413285587]
  We propose a new framework for conditional image synthesis from semantic layouts of any precision levels. The framework naturally reduces to text-to-image (T2I) at the lowest level with no shape information, and it becomes segmentation-to-image (S2I) at the highest level. We introduce several novel techniques to address the challenges coming with this new setup.
  arXiv  Detail & Related papers  (2022-11-21T18:59:05Z)
• Modeling Image Composition for Complex Scene Generation [77.10533862854706]
  We present a method that achieves state-of-the-art results on layout-to-image generation tasks. After compressing RGB images into patch tokens, we propose the Transformer with Focal Attention (TwFA) for exploring dependencies of object-to-object, object-to-patch and patch-to-patch.
  arXiv  Detail & Related papers  (2022-06-02T08:34:25Z)
• Deep Image Compositing [93.75358242750752]
  We propose a new method which can automatically generate high-quality image composites without any user input. Inspired by Laplacian pyramid blending, a dense-connected multi-stream fusion network is proposed to effectively fuse the information from the foreground and background images. Experiments show that the proposed method can automatically generate high-quality composites and outperforms existing methods both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2020-11-04T06:12:24Z)
• BachGAN: High-Resolution Image Synthesis from Salient Object Layout [78.51640906030244]
  We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout. Two main challenges spring from this new task: (i) how to generate fine-grained details and realistic textures without segmentation map input; and (ii) how to create a background and weave it seamlessly into standalone objects. By generating the hallucinated background representation dynamically, our model can synthesize high-resolution images with both photo-realistic foreground and integral background.
  arXiv  Detail & Related papers  (2020-03-26T00:54:44Z)

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.