用扩散模型直接在图上画带颜色的框，实现端到端目标检测。
GenDet: Painting Colored Bounding Boxes on Images via Diffusion Model for Object Detection
- 基于Stable Diffusion生成带语义标注的边界框
- 在COCO数据集上达到与传统检测器相当的精度
- 适合想用生成模型做视觉理解的研究者
本文提出GenDet，一种将目标检测重定义为图像生成任务的新框架。不同于传统方法，GenDet采用生成建模思路：以输入图像为条件，直接在原始图像空间中生成带语义标注的边界框。该框架基于大规模预训练的Stable Diffusion模型，构建条件生成架构，将检测任务表述为潜在空间中的语义约束。它能精确控制边界框位置和类别属性，同时保持生成模型的灵活性。该方法有效弥合了生成模型与判别任务之间的鸿沟，为构建统一视觉理解系统提供了新视角。系统性实验证明，GenDet在精度上可媲美判别式检测器，同时保留生成方法的灵活性。
原文摘要 · Abstract (English)
This paper presents GenDet, a novel framework that redefines object detection as an image generation task. In contrast to traditional approaches, GenDet adopts a pioneering approach by leveraging generative modeling: it conditions on the input image and directly generates bounding boxes with semantic annotations in the original image space. GenDet establishes a conditional generation architecture built upon the large-scale pre-trained Stable Diffusion model, formulating the detection task as semantic constraints within the latent space. It enables precise control over bounding box positions and category attributes, while preserving the flexibility of the generative model. This novel methodology effectively bridges the gap between generative models and discriminative tasks, providing a fresh perspective for constructing unified visual understanding systems. Systematic experiments demonstrate that GenDet achieves competitive accuracy compared to discriminative detectors, while retaining the flexibility characteristic of generative methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。