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

TL;DR

TWINGS introduces a TPS-based warp alignment method to improve sparse-view 3D scene reconstruction quality in Gaussian Splatting, achieving better detail and fidelity.

Contribution

It proposes a novel TPS-based initialization technique for 3D Gaussian Splatting that effectively addresses point sparsity in sparse-view scene synthesis.

Findings

Outperforms existing methods on DTU, LLFF, and Mip-NeRF360 datasets.

Enhances structural detail preservation and color fidelity in reconstructions.

Provides a fast, geometrically accurate initialization for 3D Gaussian Splatting.

Abstract

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.