Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling

Abstract

Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.

Cite

Text

Tao et al. "Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I6.28326

Markdown

[Tao et al. "Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/tao2024aaai-shadow/) doi:10.1609/AAAI.V38I6.28326

BibTeX

@inproceedings{tao2024aaai-shadow,
  title     = {{Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling}},
  author    = {Tao, Xinhao and Cao, Junyan and Hong, Yan and Niu, Li},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {5198-5206},
  doi       = {10.1609/AAAI.V38I6.28326},
  url       = {https://mlanthology.org/aaai/2024/tao2024aaai-shadow/}
}