DenseControl: Instance-Level Controllable Synthesis of Dense Crowd Image

2026-06-14

AI Summary

This work addresses the challenges of precise control over instance location and scale, as well as topological distortion, in dense crowd image synthesis. To this end, the authors propose a novel method integrating Isolated Object Embedding (IOE) maps, an Implicit Scale Embedding (ISE) strategy, and a cross-attention mechanism enhanced with positional shortcuts. This approach enables, for the first time, pixel-level accurate and topologically consistent controllable generation of dense crowds, allowing fine-grained manipulation of each instance’s position, scale, background, style, and attributes. Experimental results demonstrate that the proposed method achieves state-of-the-art performance not only in image synthesis quality but also in downstream tasks such as group analysis under data scarcity, transfer learning, and weather generalization.

Abstract

In this paper, we introduce DenseControl, a novel pipeline for generating dense crowd images. Specifically, DenseControl meticulously positions and sizes each generated instance to align precisely with the predefined coordinates and scales. Based on this, we further allow for control over the background, style, and attributes of instances. The motivation behind DenseControl stems from the observation of two main challenges in synthesizing crowd images: controlling signal embedding and maintaining topological integrity when imparting instance scale guidance. To address these, we first introduce the Isolated Object Embedding (IOE) map, a novel representation that facilitates spatial location control while mitigating the difficulties associated with learning projections for model. Secondly, we propose an Implicit Scale Embedding (ISE) strategy that seamlessly integrates with the IOE map to encode precise scale information. To further enhance the efficacy of combining ISE with the IOE map, we incorporate a Position Shortcut mechanism that enhances cross-attention to alleviate projection challenges. We evaluate DenseControl through two lenses: synthesis quality and applicability in latent applications. Experiments across different control conditions demonstrate DenseControl achieves state-of-the-art results in dense crowd image synthesis. Furthermore, we showcase applications in augmenting crowd analysis under data scarcity, transfer learning, and weather generalization scenes, to highlight the practical utility of DenseControl. The codebase will be released.

Problem

• dense crowd synthesis
• instance-level control
• spatial positioning
• scale guidance
• topological integrity

Innovation

• DenseControl
• Isolated Object Embedding
• Implicit Scale Embedding
• instance-level control
• crowd image synthesis