Learning Flow Fields in Attention for Controllable Person Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915060460290048 |
|---|---|
| author | Zhou, Zijian Liu, Shikun Han, Xiao Liu, Haozhe Ng, Kam Woh Xie, Tian Cong, Yuren Li, Hang Xu, Mengmeng Pérez-Rúa, Juan-Manuel Patel, Aditya Xiang, Tao Shi, Miaojing He, Sen |
| author_facet | Zhou, Zijian Liu, Shikun Han, Xiao Liu, Haozhe Ng, Kam Woh Xie, Tian Cong, Yuren Li, Hang Xu, Mengmeng Pérez-Rúa, Juan-Manuel Patel, Aditya Xiang, Tao Shi, Miaojing He, Sen |
| contents | Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person's appearance or pose. However, prior methods often distort fine-grained textural details from the reference image, despite achieving high overall image quality. We attribute these distortions to inadequate attention to corresponding regions in the reference image. To address this, we thereby propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key in the attention layer during training. Specifically, it is realized via a regularization loss on top of the attention map within a diffusion-based baseline. Our extensive experiments show that Leffa achieves state-of-the-art performance in controlling appearance (virtual try-on) and pose (pose transfer), significantly reducing fine-grained detail distortion while maintaining high image quality. Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08486 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Flow Fields in Attention for Controllable Person Image Generation Zhou, Zijian Liu, Shikun Han, Xiao Liu, Haozhe Ng, Kam Woh Xie, Tian Cong, Yuren Li, Hang Xu, Mengmeng Pérez-Rúa, Juan-Manuel Patel, Aditya Xiang, Tao Shi, Miaojing He, Sen Computer Vision and Pattern Recognition Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person's appearance or pose. However, prior methods often distort fine-grained textural details from the reference image, despite achieving high overall image quality. We attribute these distortions to inadequate attention to corresponding regions in the reference image. To address this, we thereby propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key in the attention layer during training. Specifically, it is realized via a regularization loss on top of the attention map within a diffusion-based baseline. Our extensive experiments show that Leffa achieves state-of-the-art performance in controlling appearance (virtual try-on) and pose (pose transfer), significantly reducing fine-grained detail distortion while maintaining high image quality. Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models. |
| title | Learning Flow Fields in Attention for Controllable Person Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.08486 |