ReCo: Region-Controlled Text-to-Image Generation

By Zhengyuan Yang, Jianfeng Wang, Zhe Gan, Linjie Li, Kevin Qinghong Lin, Chenfei Wu, Nan Duan, Zicheng Liu, Ce Liu, Michael Zeng and 1 more. 2022

214 citations recorded by the source corpus.

Recently, large-scale text-to-image (T2I) models have shown impressive performance in generating high-fidelity images, but with limited controllability, e.g., precisely specifying the content in a specific region with a free-form text description. In this paper, we propose an effective technique for such regional control in T2I generation. We augment T2I models' inputs with an extra set of position tokens, which represent the quantized spatial coordinates. Each region is specified by four position tokens to represent the top-left and bottom-right corners, followed by an open-ended natural language regional description. Then, we fine-tune a pre-trained T2I model with such new input interface. Our model, dubbed as ReCo (Region-Controlled T2I), enables the region control for arbitrary objects described by open-ended regional texts rather than by object labels from a constrained category set. Empirically, ReCo achieves better image quality than the T2I model strengthened by positional words (FID: 8.82 → 7.36, SceneFID: 15.54 → 6.51 on COCO), together with objects being more accurately placed, amounting to a 20.40% region classification accuracy improvement on COCO. Furthermore, we demonstrate that ReCo can better control the object count, spatial relationship, and region attributes such as color/size, with the free-form regional description. Human evaluation on PaintSkill shows that ReCo is +19.28% and +17.21% more accurate in generating images with correct object count and spatial relationship than the T2I model. Code is available at https://github.com/microsoft/Reeo.

Subfields: Computer Vision and Pattern Recognition, Generative Models, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

In Multimodal Learning

Citations in the corpus

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion (2023, background): “Recently, fine-tuning Stable Diffusion models to adhere to additional layout information has also been explored in [18] and [37].”
Training-Free Layout Control with Cross-Attention Guidance (2023, unknown): “Then, the network D returns an estimate”
SDDGR: Stable Diffusion-Based Deep Generative Replay for Class Incremental Object Detection (2024, background): “This has led to various studies [32, 65, 69, 70] to utilize the model’s capabilities with its original weights fixed.”
LayoutGPT: Compositional Visual Planning and Generation with Large Language Models (2023, methodology): “11 in the Appendix visualizes the results of attribute binding using LayoutGPT and ReCo [56].”