Semantically Consistent Person Image Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910834866782208 |
|---|---|
| author | Roy, Prasun Bhattacharya, Saumik Ghosh, Subhankar Pal, Umapada Blumenstein, Michael |
| author_facet | Roy, Prasun Bhattacharya, Saumik Ghosh, Subhankar Pal, Umapada Blumenstein, Michael |
| contents | We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps. At first, we employ a Pix2PixHD model to infer a coarse semantic mask that represents the new person's spatial location, scale, and potential pose. Next, we use a data-centric approach to select the closest representation from a precomputed cluster of fine semantic masks. Finally, we adopt a multi-scale, attention-guided architecture to transfer the appearance attributes from an exemplar image. The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context. We conclude our findings with relevant qualitative and quantitative evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_14728 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Semantically Consistent Person Image Generation Roy, Prasun Bhattacharya, Saumik Ghosh, Subhankar Pal, Umapada Blumenstein, Michael Computer Vision and Pattern Recognition Multimedia We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps. At first, we employ a Pix2PixHD model to infer a coarse semantic mask that represents the new person's spatial location, scale, and potential pose. Next, we use a data-centric approach to select the closest representation from a precomputed cluster of fine semantic masks. Finally, we adopt a multi-scale, attention-guided architecture to transfer the appearance attributes from an exemplar image. The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context. We conclude our findings with relevant qualitative and quantitative evaluations. |
| title | Semantically Consistent Person Image Generation |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2302.14728 |