GenDet: Painting Colored Bounding Boxes on Images via Diffusion Model for Object Detection

2026-01-12

AI Summary

This work proposes a novel approach that reformulates object detection as an image generation task, addressing the longstanding incompatibility between traditional detection methods and generative models. By leveraging Stable Diffusion, the authors introduce the first end-to-end conditional generative architecture that directly synthesizes colored bounding boxes—embedded with class semantics and spatial coordinates—in the original image space. Precise control over box generation is achieved through semantic constraints imposed in the latent space, effectively bridging the gap between generative and discriminative paradigms in computer vision. The method preserves the inherent flexibility of generative models while achieving detection accuracy comparable to that of state-of-the-art discriminative detectors.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• object detection
• image generation
• generative modeling
• bounding boxes
• semantic annotations

Innovation

• diffusion model
• object detection
• image generation
• conditional generation
• Stable Diffusion