FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution
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_ | 1866916460882821120 |
|---|---|
| author | Wang, Shuai Li, Zexian Song, Tianhui Li, Xubin Ge, Tiezheng Zheng, Bo Wang, Limin |
| author_facet | Wang, Shuai Li, Zexian Song, Tianhui Li, Xubin Ge, Tiezheng Zheng, Bo Wang, Limin |
| contents | Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality. Existing transformer-based diffusion methods suffer from quadratic computation cost and limited resolution extrapolation capabilities, making them less effective for this task. In this paper, we propose FlowDCN, a purely convolution-based generative model with linear time and memory complexity, that can efficiently generate high-quality images at arbitrary resolutions. Equipped with a new design of learnable group-wise deformable convolution block, our FlowDCN yields higher flexibility and capability to handle different resolutions with a single model. FlowDCN achieves the state-of-the-art 4.30 sFID on $256\times256$ ImageNet Benchmark and comparable resolution extrapolation results, surpassing transformer-based counterparts in terms of convergence speed (only $\frac{1}{5}$ images), visual quality, parameters ($8\%$ reduction) and FLOPs ($20\%$ reduction). We believe FlowDCN offers a promising solution to scalable and flexible image synthesis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22655 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution Wang, Shuai Li, Zexian Song, Tianhui Li, Xubin Ge, Tiezheng Zheng, Bo Wang, Limin Computer Vision and Pattern Recognition Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality. Existing transformer-based diffusion methods suffer from quadratic computation cost and limited resolution extrapolation capabilities, making them less effective for this task. In this paper, we propose FlowDCN, a purely convolution-based generative model with linear time and memory complexity, that can efficiently generate high-quality images at arbitrary resolutions. Equipped with a new design of learnable group-wise deformable convolution block, our FlowDCN yields higher flexibility and capability to handle different resolutions with a single model. FlowDCN achieves the state-of-the-art 4.30 sFID on $256\times256$ ImageNet Benchmark and comparable resolution extrapolation results, surpassing transformer-based counterparts in terms of convergence speed (only $\frac{1}{5}$ images), visual quality, parameters ($8\%$ reduction) and FLOPs ($20\%$ reduction). We believe FlowDCN offers a promising solution to scalable and flexible image synthesis. |
| title | FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.22655 |