Synthesizing Environment-Specific People in Photographs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912046809874432 |
|---|---|
| author | Ostrek, Mirela O'Sullivan, Carol Black, Michael J. Thies, Justus |
| author_facet | Ostrek, Mirela O'Sullivan, Carol Black, Michael J. Thies, Justus |
| contents | We present ESP, a novel method for context-aware full-body generation, that enables photo-realistic synthesis and inpainting of people wearing clothing that is semantically appropriate for the scene depicted in an input photograph. ESP is conditioned on a 2D pose and contextual cues that are extracted from the photograph of the scene and integrated into the generation process, where the clothing is modeled explicitly with human parsing masks (HPM). Generated HPMs are used as tight guiding masks for inpainting, such that no changes are made to the original background. Our models are trained on a dataset containing a set of in-the-wild photographs of people covering a wide range of different environments. The method is analyzed quantitatively and qualitatively, and we show that ESP outperforms the state-of-the-art on the task of contextual full-body generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_14579 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Synthesizing Environment-Specific People in Photographs Ostrek, Mirela O'Sullivan, Carol Black, Michael J. Thies, Justus Computer Vision and Pattern Recognition We present ESP, a novel method for context-aware full-body generation, that enables photo-realistic synthesis and inpainting of people wearing clothing that is semantically appropriate for the scene depicted in an input photograph. ESP is conditioned on a 2D pose and contextual cues that are extracted from the photograph of the scene and integrated into the generation process, where the clothing is modeled explicitly with human parsing masks (HPM). Generated HPMs are used as tight guiding masks for inpainting, such that no changes are made to the original background. Our models are trained on a dataset containing a set of in-the-wild photographs of people covering a wide range of different environments. The method is analyzed quantitatively and qualitatively, and we show that ESP outperforms the state-of-the-art on the task of contextual full-body generation. |
| title | Synthesizing Environment-Specific People in Photographs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.14579 |