Proxy-Free Gaussian Splats Deformation with Splat-Based Surface Estimation

2025-11-24

AI Summary

Existing Gaussian splatting (GS) deformation methods rely on proxy structures—such as cages or grids—leading to limited deformation quality and high computational overhead; conversely, direct application of Laplacian deformation to point clouds lacks structural awareness, resulting in inaccurate surface modeling. To address this, we propose SpLap, a proxy-free Gaussian splatting deformation framework. SpLap constructs a surface-aware point lattice graph for the first time, defines neighborhoods via spatial intersection, and introduces a Gaussian-kernel adaptive mechanism to compute structure-sensitive Laplacian operators. By eliminating explicit proxies, SpLap significantly improves topological preservation and geometric fidelity. Extensive experiments on four benchmark datasets—including ShapeNet—with 50 complex objects demonstrate that SpLap outperforms both proxy-based and state-of-the-art proxy-free baselines in deformation accuracy and rendered visual quality.

Technology Category

• Machine Learning: Learning with Manifolds
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We introduce SpLap, a proxy-free deformation method for Gaussian splats (GS) based on a Laplacian operator computed from our novel surface-aware splat graph. Existing approaches to GS deformation typically rely on deformation proxies such as cages or meshes, but they suffer from dependency on proxy quality and additional computational overhead. An alternative is to directly apply Laplacian-based deformation techniques by treating splats as point clouds. However, this often fail to properly capture surface information due to lack of explicit structure. To address this, we propose a novel method that constructs a surface-aware splat graph, enabling the Laplacian operator derived from it to support more plausible deformations that preserve details and topology. Our key idea is to leverage the spatial arrangement encoded in splats, defining neighboring splats not merely by the distance between their centers, but by their intersections. Furthermore, we introduce a Gaussian kernel adaptation technique that preserves surface structure under deformation, thereby improving rendering quality after deformation. In our experiments, we demonstrate the superior performance of our method compared to both proxy-based and proxy-free baselines, evaluated on 50 challenging objects from the ShapeNet, Objaverse, and Sketchfab datasets, as well as the NeRF-Synthetic dataset. Code is available at https://github.com/kjae0/SpLap.

Problem

• Develops proxy-free deformation for Gaussian splats using surface-aware graphs
• Eliminates dependency on deformation proxies like cages or meshes
• Preserves surface details and topology during deformation process

Innovation

• Proxy-free deformation using surface-aware splat graph
• Laplacian operator derived from splat intersections
• Gaussian kernel adaptation preserves surface structure