Modern diffusion-based image generative models have made significant progress
and become promising to enrich training data for the object detection task.
However, the generation quality and the controllability for complex scenes
containing multi-class objects and dense objects with occlusions remain
limited. This paper presents ODGEN, a novel method to generate high-quality
images conditioned on bounding boxes, thereby facilitating data synthesis for
object detection. Given a domain-specific object detection dataset, we first
fine-tune a pre-trained diffusion model on both cropped foreground objects and
entire images to fit target distributions. Then we propose to control the
diffusion model using synthesized visual prompts with spatial constraints and
object-wise textual descriptions. ODGEN exhibits robustness in handling complex
scenes and specific domains. Further, we design a dataset synthesis pipeline to
evaluate ODGEN on 7 domain-specific benchmarks to demonstrate its
effectiveness. Adding training data generated by ODGEN improves up to 25.3%
mAP@.50:.95 with object detectors like YOLOv5 and YOLOv7, outperforming prior
controllable generative methods. In addition, we design an evaluation protocol
based on COCO-2014 to validate ODGEN in general domains and observe an
advantage up to 5.6% in mAP@.50:.95 against existing methods.

ODGEN 是一种新的条件高质量图像生成方法，用于生成复杂场景中多类对象和具有遮挡的密集对象，进而促进目标检测数据的合成。通过在裁剪的前景对象和整个图像上对预训练的扩散模型进行微调，再借助合成的视觉提示和对象描述来控制扩散模型，ODGEN 在处理复杂场景和特定领域方面表现出了鲁棒性，并通过数据集合成管道在 7 个特定领域的基准测试中进行了评估以展示其有效性，与 YOLOv5 和 YOLOv7 等对象检测器相比，添加 ODGEN 生成的训练数据可以将 mAP@.50:.95 改善高达 25.3%，而且在基于 COCO-2014 的评估协议下，ODGEN 在一般领域中的 mAP@.50:.95 优势高达 5.6%。