Scene Aware Person Image Generation through Global Contextual Conditioning
Document Type
Conference Article
Publication Title
Proceedings - International Conference on Pattern Recognition
Abstract
Person image generation is an intriguing yet challenging problem. However, this task becomes even more difficult under constrained situations. In this work, we propose a novel pipeline to generate and insert contextually relevant person images into an existing scene while preserving the global semantics. More specifically, we aim to insert a person such that the location, pose, and scale of the person being inserted blends in with the existing persons in the scene. Our method uses three individual networks in a sequential pipeline. At first, we predict the potential location and the skeletal structure of the new person by conditioning a Wasserstein Generative Adversarial Network (WGAN) on the existing human skeletons present in the scene. Next, the predicted skeleton is refined through a shallow linear network to achieve higher structural accuracy in the generated image. Finally, the target image is generated from the refined skeleton using another generative network conditioned on a given image of the target person. In our experiments, we achieve high-resolution photo-realistic generation results while preserving the general context of the scene. We conclude our paper with multiple qualitative and quantitative benchmarks on the results.
First Page
2764
Last Page
2770
DOI
10.1109/ICPR56361.2022.9956682
Publication Date
1-1-2022
Recommended Citation
Roy, Prasun; Ghosh, Subhankar; Bhattacharya, Saumik; Pal, Umapada; and Blumenstein, Michael, "Scene Aware Person Image Generation through Global Contextual Conditioning" (2022). Conference Articles. 469.
https://digitalcommons.isical.ac.in/conf-articles/469
Comments
Open Access, Green