L-DiffER: Single Image Reflection Removal with Language-Based Diffusion Model

Abstract

In this paper, we introduce L-DiffER, a language-based diffusion model designed for the ill-posed single image reflection removal task. Although having shown impressive performance for image generation, existing language-based diffusion models struggle with precise control and faithfulness in image restoration. To overcome these limitations, we propose an iterative condition refinement strategy to resolve the problem of inaccurate control conditions. A multi-condition constraint mechanism is employed to ensure the recovery faithfulness of image color and structure while retaining the generation capability to handle low-transmitted reflections. We demonstrate the superiority of the proposed method through extensive experiments, showcasing both quantitative and qualitative improvements over existing methods.

Cite

Text

Hong et al. "L-DiffER: Single Image Reflection Removal with Language-Based Diffusion Model." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72661-3_4

Markdown

[Hong et al. "L-DiffER: Single Image Reflection Removal with Language-Based Diffusion Model." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/hong2024eccv-ldiffer/) doi:10.1007/978-3-031-72661-3_4

BibTeX

@inproceedings{hong2024eccv-ldiffer,
  title     = {{L-DiffER: Single Image Reflection Removal with Language-Based Diffusion Model}},
  author    = {Hong, Yuchen and Zhong, Haofeng and Weng, Shuchen and Liang, Jinxiu S and Shi, Boxin},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2024},
  doi       = {10.1007/978-3-031-72661-3_4},
  url       = {https://mlanthology.org/eccv/2024/hong2024eccv-ldiffer/}
}