TWINGS：面向稀疏视角高斯泼溅的薄板样条形变对齐初始化
TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
用薄板样条把单目深度反投影点对齐到三角化控制点，为 3DGS 提供几何一致的稠密初始化；做稀疏视角重建时可直接替换随机初始化或 SfM 点云初始化环节。
原文依据 TWINGS provides a fast and geometrically accurate initialization for 3DGS
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从稀疏视角输入进行新视角合成是三维计算机视觉中的一项重大挑战，尤其是在视角有限的情况下实现高质量场景重建。我们提出 TWINGS，一个通过直接解决点稀疏性问题来增强三维高斯泼溅（3DGS）的框架。我们采用薄板样条（TPS）——一种通过最小化弯曲能量来估计全局连贯形变的平滑非刚性形变模型——将从估计深度反投影得到的点与三角化的三维控制点对齐，从而得到校准后的反投影点。通过在这些校准点中靠近控制点的位置进行采样，TWINGS 为 3DGS 提供了一种快速且几何精确的初始化，最终改善了重建场景中的结构细节保持与颜色保真度。在 DTU、LLFF 和 Mip-NeRF360 上的大量实验表明，TWINGS 持续优于现有方法，在稀疏视角场景下实现了细节丰富且准确的重建。
英文原文摘要 1034 字符
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.