通过随机丢弃高斯分布提升稀疏视角渲染效果
DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
- 引入随机丢弃正则化，降低模型复杂度防止过拟合
- 在少量视角下仍能保持高质量渲染，优于现有方法
- 适合需要高效泛化的3D重建与新视角生成场景
尽管3D高斯点阵（3DGS）在新视角合成中表现优异，但在稀疏输入下性能显著下降并产生不良伪影。随着训练视角减少，新视角合成问题变为高度欠定，现有方法普遍面临严重过拟合问题。我们发现，高斯原型数量较少的模型在稀疏输入下过拟合更轻。受此启发，提出随机丢弃正则化（RDR），利用低复杂度模型优势缓解过拟合。此外，为弥补此类模型高频细节缺失，设计边缘引导分裂策略（ESS）。结合两项技术，所提方法（DropoutGS）是一种简单有效的即插即用方案，可显著提升现有3DGS方法在稀疏视图下的泛化能力。大量实验表明，其在Blender、LLFF和DTU等基准数据集上均实现稀疏视图下的最先进性能。
原文摘要 · Abstract (English)
Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/.
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。