CVLGMay 21

TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting

arXiv:2605.2206930.6
AI Analysis

For 3D computer vision researchers, TWINGS offers a practical solution to the sparse-view reconstruction problem, achieving high-quality results with limited viewpoints.

TWINGS improves 3D Gaussian Splatting for sparse-view novel view synthesis by using Thin Plate Splines to align backprojected points with triangulated control points, providing better initialization. It consistently outperforms existing methods on DTU, LLFF, and Mip-NeRF360 datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes