GLIGEN：开放集定位的文本到图像生成
GLIGEN: Open-Set Grounded Text-to-Image Generation
AI总结：
本文提出GLIGEN，通过冻结预训练扩散模型权重并利用门控机制注入定位信息，实现以标题和边界框为条件的开放世界定位文本到图像生成，在COCO和LVIS上零样本性能大幅超越现有基线。
摘要：
大规模文本到图像扩散模型已取得惊人进展。然而，现状是仅使用文本输入，这可能阻碍可控性。在这项工作中，我们提出GLIGEN，即定位语言到图像生成（Grounded-Language-to-Image Generation），这是一种新颖的方法，它构建于现有预训练文本到图像扩散模型之上并扩展其功能，使其也能以定位输入为条件。为保留预训练模型庞大的概念知识，我们冻结其全部权重，并通过门控机制将定位信息注入新的可训练层。我们的模型实现了具有标题和边界框条件输入的开放世界定位文本到图像生成，且定位能力能很好地泛化到新的空间配置和概念。GLIGEN在COCO和LVIS上的零样本性能大幅优于现有监督式布局到图像基线。
英文摘要：
Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism. Our model achieves open-world grounded text2img generation with caption and bounding box condition inputs, and the grounding ability generalizes well to novel spatial configurations and concepts. GLIGEN's zero-shot performance on COCO and LVIS outperforms that of existing supervised layout-to-image baselines by a large margin.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
