一个模型同时完成点云补全、升频、去噪和着色，效率更高。
SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
- 用三层条件扩散框架，融合多种缺陷间的关联信息。
- 在四个任务上均超越专用模型，且避免逐个处理的误差累积。
- 适合需要高效处理复杂点云缺陷的自动驾驶与三维重建场景。
点云处理任务如补全、升频、去噪和着色在自动驾驶与三维重建中至关重要。尽管已有显著进展，但以往方法多独立处理各项任务，使用专用模型。然而，这些缺陷（不完整、低分辨率、噪声、缺色）常同时存在且相互影响，依次应用模型会导致误差累积和计算开销增加。为此，我们提出SuperPC，首个可同时处理这四项任务的统一扩散模型。采用三层条件扩散框架，并引入新颖的空间混合融合策略，有效利用各类缺陷间的相关性，实现高效协同处理。实验表明，SuperPC在四项任务上均优于现有最先进专用模型及其组合方案。
原文摘要 · Abstract (English)
Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite substantial advancements, prior approaches often address each of these tasks independently, with separate models focused on individual issues. However, this isolated approach fails to account for the fact that defects like incompleteness, low resolution, noise, and lack of color frequently coexist, with each defect influencing and correlating with the others. Simply applying these models sequentially can lead to error accumulation from each model, along with increased computational costs. To address these challenges, we introduce SuperPC, the first unified diffusion model capable of concurrently handling all four tasks. Our approach employs a three-level-conditioned diffusion framework, enhanced by a novel spatial-mix-fusion strategy, to leverage the correlations among these four defects for simultaneous, efficient processing. We show that SuperPC outperforms the state-of-the-art specialized models as well as their combination on all four individual tasks.
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。