用2D扩散模型补全不完整的3D点云，保持原有结构不失真。
GSComplete: Gaussian Splat Completion with 2D Diffusion Priors
- 结合得分蒸馏采样与新设计的保留损失，仅用2D先验补全缺失区域。
- 在新数据集上相比现有方法显著提升输入结构保留精度。
- 适合需要高保真3D重建且无3D训练数据的场景。
高斯点阵能快速高效地表示3D物体，但实际中常因输入数据不完整而出现缺失区域。现有补全方法要么无法保留原始点阵，要么依赖稀缺的3D训练数据。我们提出GSComplete，将基于得分蒸馏采样的3D生成与一种新型保留损失相结合，确保原始点阵在应可见处被保留。该方法仅利用2D扩散先验即可完成点阵补全，完全保留已有点阵并仅在缺失区域生成新点阵，且不遮挡输入。为评估该方法，我们构建了一个包含部分高斯点阵的新数据集，并证明其在输入保留精度上显著优于现有方法，同时生成结果具有相当的合理性。代码与数据集将在论文接受后公开。
原文摘要 · Abstract (English)
Gaussian splats provide a fast, high-fidelity representation for 3D objects but are often constructed from incomplete input data in practice, leaving missing regions. Existing completion methods either do not preserve the original splats or require scarcely available 3D training data. We propose GSComplete, which combines 3D generation based on Score Distillation Sampling with a novel preservation loss that encourages the original splats to be preserved where they should be visible. This effectively completes the Gaussian splat object using only 2D diffusion priors while fully preserving existing splats and generating new splats only in missing regions, without occluding the input. To evaluate our approach, we introduce a new dataset of partial Gaussian splat objects and show that GSComplete achieves significantly more accurate preservation of the input than existing methods with comparable plausibility of the completed result. Our code and dataset will be made available upon acceptance.
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。