用薄板样条优化稀疏视角下的3D高斯点云初始化，提升重建质量。
TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
- 用薄板样条建模非刚性形变，对齐深度反投影点与三角化控制点
- 在DTU/LLFF/Mip-NeRF360上实现更清晰的结构细节和色彩保真度
- 适合需要稀疏视角高质量重建的研究者和工业应用
从稀疏视角进行新视角合成是三维计算机视觉中的重大挑战，尤其在有限视角下实现高质量场景重建。本文提出TWINGS框架，通过直接处理点云稀疏性来增强3D高斯点阵（3DGS）性能。采用薄板样条（TPS）这一平滑非刚性形变模型，以最小化弯曲能量的方式，从控制点对应关系中估计全局一致的形变场，将估计深度的反投影点与三角化得到的3D控制点对齐，从而获得校准后的反投影点。通过在控制点附近采样这些校准点，TWINGS为3DGS提供快速且几何精确的初始化，显著提升了重建场景的结构细节保留与颜色保真度。在DTU、LLFF和Mip-NeRF360数据集上的大量实验表明，该方法在稀疏视角条件下持续优于现有方法，能够生成更加精细准确的重建结果。
原文摘要 · Abstract (English)
Novel view synthesis from sparse-view inputs poses a significant challenge in 3D computer vision, particularly for achieving high-quality scene reconstructions with limited viewpoints. We introduce TWINGS, a framework that enhances 3D Gaussian Splatting (3DGS) by directly addressing point sparsity. We employ Thin Plate Splines (TPS), a smooth non-rigid deformation model that minimizes bending energy to estimate a globally coherent warp from control-point correspondences, to align backprojected points from estimated depth with triangulated 3D control points, yielding calibrated backprojected points. By sampling these calibrated points near the control points, TWINGS provides a fast and geometrically accurate initialization for 3DGS, ultimately improving structural detail preservation and color fidelity in reconstructed scenes. Extensive experiments on DTU, LLFF, and Mip-NeRF360 demonstrate that TWINGS consistently outperforms existing methods, delivering detailed and accurate reconstructions under sparse-view scenarios.
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。