# GenDet: Painting Colored Bounding Boxes on Images via Diffusion Model for Object Detection Source: [GenDet: Painting Colored Bounding Boxes on Images via Diffusion Model for Object Detection]() Collection index: [llms.txt]() Data updated: 2026-01-14T05:00:12.520Z Authors: Chen Min, Chengyang Li, Fanjie Kong, Qi Zhu, Dawei Zhao, Liang Xiao Published: 2026-01-12T07:29:59.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on CrowdHuman (AP50, mMR, Recall)](): Object Detection; CrowdHuman; AP50: 52.3. - [Object Detection on COCO 2017 (val)](): Object Detection; COCO 2017 (val); AP: 46.4. ## Original sources and implementation [Original paper]() [PDF]()