Abstract
This work introduces InJecteD, a framework for interpreting Denoising Diffusion Probabilistic Models (DDPMs) by analyzing sample trajectories during the denoising process of 2D point cloud generation. We apply this framework to three datasets from the Datasaurus Dozen bullseye, dino, and circle using a simplified DDPM architecture with customizable input and time embeddings. Our approach quantifies trajectory properties, including displacement, velocity, clustering, and drift field dynamics, using statistical metrics such as Wasserstein distance and cosine similarity. By enhancing model transparency, InJecteD supports human AI collaboration by enabling practitioners to debug and refine generative models. Experiments reveal distinct denoising phases: initial noise exploration, rapid shape formation, and final refinement, with dataset-specific behaviors example, bullseyes concentric convergence vs. dinos complex contour formation. We evaluate four model configurations, varying embeddings and noise schedules, demonstrating that Fourier based embeddings improve trajectory stability and reconstruction quality
Abstract (translated)
这项工作介绍了一种名为InJecteD的框架，该框架通过分析在二维点云生成过程中去噪扩散概率模型（DDPMs）样本轨迹来解释这些模型。我们使用一个简化版的具有可定制输入和时间嵌入的DDPM架构，在Datasaurus Dozen数据集中的bullseye、dino和circle三个子集中应用了这一框架。我们的方法通过诸如Wasserstein距离和余弦相似度等统计指标量化轨迹属性，包括位移、速度、聚类和漂移场动态。通过增强模型的透明性，InJecteD支持人类与AI的合作，使实践者能够调试并改进生成式模型。 实验揭示了去噪过程中的三个不同阶段：初始噪声探索期、快速形状形成期以及最终精炼期，并且这些行为会因数据集的不同而有所差异。例如，在bullseye中观察到了同心收敛的行为，而在dino中则形成了复杂的轮廓。我们评估了四种模型配置，通过改变嵌入和噪声调度来展示基于傅里叶的嵌入如何提高轨迹稳定性以及重建质量。
URL
https://arxiv.org/abs/2509.12239
