Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916857575899136 |
|---|---|
| author | Guo, Ziyu Zhang, Renrui Tong, Chengzhuo Zhao, Zhizheng Huang, Rui Zhang, Haoquan Zhang, Manyuan Liu, Jiaming Zhang, Shanghang Gao, Peng Li, Hongsheng Heng, Pheng-Ann |
| author_facet | Guo, Ziyu Zhang, Renrui Tong, Chengzhuo Zhao, Zhizheng Huang, Rui Zhang, Haoquan Zhang, Manyuan Liu, Jiaming Zhang, Shanghang Gao, Peng Li, Hongsheng Heng, Pheng-Ann |
| contents | Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be applied to verifying and reinforcing image generation scenarios. In this paper, we provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation. We focus on three techniques: scaling test-time computation for verification, aligning model preferences with Direct Preference Optimization (DPO), and integrating these techniques for complementary effects. Our results demonstrate that these approaches can be effectively adapted and combined to significantly improve image generation performance. Furthermore, given the pivotal role of reward models in our findings, we propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation. PARM adaptively assesses each generation step through a potential assessment approach, merging the strengths of existing reward models, and PARM++ further introduces a reflection mechanism to self-correct the generated unsatisfactory image, which is the first to incorporate reflection in autoregressive image generation. Using our investigated reasoning strategies, we enhance a baseline model, Show-o, to achieve superior results, with a significant +24% improvement on the GenEval benchmark, surpassing Stable Diffusion 3 by +15%. We hope our study provides unique insights and paves a new path for integrating CoT reasoning with autoregressive image generation. Code and models are released at https://github.com/ZiyuGuo99/Image-Generation-CoT |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13926 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step Guo, Ziyu Zhang, Renrui Tong, Chengzhuo Zhao, Zhizheng Huang, Rui Zhang, Haoquan Zhang, Manyuan Liu, Jiaming Zhang, Shanghang Gao, Peng Li, Hongsheng Heng, Pheng-Ann Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be applied to verifying and reinforcing image generation scenarios. In this paper, we provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation. We focus on three techniques: scaling test-time computation for verification, aligning model preferences with Direct Preference Optimization (DPO), and integrating these techniques for complementary effects. Our results demonstrate that these approaches can be effectively adapted and combined to significantly improve image generation performance. Furthermore, given the pivotal role of reward models in our findings, we propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation. PARM adaptively assesses each generation step through a potential assessment approach, merging the strengths of existing reward models, and PARM++ further introduces a reflection mechanism to self-correct the generated unsatisfactory image, which is the first to incorporate reflection in autoregressive image generation. Using our investigated reasoning strategies, we enhance a baseline model, Show-o, to achieve superior results, with a significant +24% improvement on the GenEval benchmark, surpassing Stable Diffusion 3 by +15%. We hope our study provides unique insights and paves a new path for integrating CoT reasoning with autoregressive image generation. Code and models are released at https://github.com/ZiyuGuo99/Image-Generation-CoT |
| title | Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2501.13926 |