TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition

Page view(s)
43
Checked on Apr 11, 2025
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
Title:
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
Journal Title:
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Keywords:
Publication Date:
15 January 2024
Citation:
Lu, S., Liu, Y., & Kong, A. W.-K. (2023, October 1). TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.00218
Abstract:
Text-driven diffusion models have exhibited impressive generative capabilities, enabling various image editing tasks. In this paper, we propose TF-ICON, a novel Training-Free Image COmpositioN framework that harnesses the power of text-driven diffusion models for crossdomain image-guided composition. This task aims to seamlessly integrate user-provided objects into a specific visual context. Current diffusion-based methods often involve costly instance-based optimization or finetuning of pretrained models on customized datasets, which can potentially undermine their rich prior. In contrast, TF-ICON can leverage off-the-shelf diffusion models to perform crossdomain image-guided composition without requiring additional training, finetuning, or optimization. Moreover, we introduce the exceptional prompt, which contains no information, to facilitate text-driven diffusion models in accurately inverting real images into latent representations, forming the basis for compositing. Our experiments show that equipping Stable Diffusion with the exceptional prompt outperforms state-of-the-art inversion methods on various datasets (CelebA-HQ, COCO, and ImageNet), and that TFICON surpasses prior baselines in versatile visual domains. Code is available at https://github.com/Shilin-LU/TF-ICON
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - Strategic Capability Research Centres Funding Initiative
Grant Reference no. : N.A
Description:
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
10.1109/ICCV51070.2023.00218
Files uploaded:

File Size Format Action
11210-diffusion-shilinyz.pdf 4.01 MB PDF Request a copy