RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917835833344000 |
|---|---|
| author | Wang, Benzhi Zhou, Jingkai Bai, Jingqi Yang, Yang Chen, Weihua Wang, Fan Lei, Zhen |
| author_facet | Wang, Benzhi Zhou, Jingkai Bai, Jingqi Yang, Yang Chen, Weihua Wang, Fan Lei, Zhen |
| contents | In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating images of humans with realistic semantic parts, such as hands and faces, remains a significant challenge due to their intricate structural complexity. To address this issue, we propose a novel post-processing solution named RealisHuman. The RealisHuman framework operates in two stages. First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image. Second, it seamlessly integrates the rectified human parts back into their corresponding positions by repainting the surrounding areas to ensure smooth and realistic blending. The RealisHuman framework significantly enhances the realism of human generation, as demonstrated by notable improvements in both qualitative and quantitative metrics. Code is available at https://github.com/Wangbenzhi/RealisHuman. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_03644 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images Wang, Benzhi Zhou, Jingkai Bai, Jingqi Yang, Yang Chen, Weihua Wang, Fan Lei, Zhen Computer Vision and Pattern Recognition In recent years, diffusion models have revolutionized visual generation, outperforming traditional frameworks like Generative Adversarial Networks (GANs). However, generating images of humans with realistic semantic parts, such as hands and faces, remains a significant challenge due to their intricate structural complexity. To address this issue, we propose a novel post-processing solution named RealisHuman. The RealisHuman framework operates in two stages. First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image. Second, it seamlessly integrates the rectified human parts back into their corresponding positions by repainting the surrounding areas to ensure smooth and realistic blending. The RealisHuman framework significantly enhances the realism of human generation, as demonstrated by notable improvements in both qualitative and quantitative metrics. Code is available at https://github.com/Wangbenzhi/RealisHuman. |
| title | RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.03644 |