通过分析去噪过程轨迹，揭示点云生成中形状演化规律。
InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation
- 用统计方法量化去噪路径的位移、速度与聚类特征。
- 发现三阶段生成过程：噪声探索、快速成形、精细优化。
- 适合关注生成模型可解释性与调试的开发者使用。
本文提出InJecteD框架，用于解析2D点云生成中去噪扩散概率模型（DDPM）的样本轨迹。针对Datasaurus Dozen中的bullseye、dino、circle三个数据集，采用可定制输入与时间嵌入的简化DDPM架构，通过Wasserstein距离和余弦相似度等统计指标，量化轨迹的位移、速度、聚类特性及漂移场动态。实验揭示了三阶段去噪过程：初始噪声探索、快速形状形成、最终精细调整，不同数据集呈现特异性行为，如bullseye的同心收敛与dino的复杂轮廓构建。对比四种模型配置（嵌入方式与噪声调度），结果表明基于傅里叶的嵌入能提升轨迹稳定性与重建质量。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。