SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors

2026-02-02

AI Summary

Sparse-view 3D scene reconstruction often yields fragmented point clouds with color bias and high-resolution artifacts due to insufficient geometric continuity. To address this, this work proposes SurfSplat—a feedforward framework built upon 2D Gaussian Splatting (2DGS)—which introduces, for the first time, a surface continuity prior combined with a forced alpha blending strategy to significantly enhance geometric coherence and texture fidelity. Additionally, the paper presents a novel evaluation metric, High-Resolution Rendering Consistency (HRRC), to better assess reconstruction quality. Experimental results demonstrate that SurfSplat consistently outperforms existing methods on RealEstate10K, DL3DV, and ScanNet datasets, achieving state-of-the-art performance in both standard metrics and HRRC for high-quality sparse-view 3D reconstruction.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches leverage generalizable models to generate 3D scenes using 3D Gaussian Splatting (3DGS) primitive. However, they often fail to produce continuous surfaces and instead yield discrete, color-biased point clouds that appear plausible at normal resolution but reveal severe artifacts under close-up views. To address this issue, we present SurfSplat, a feedforward framework based on 2D Gaussian Splatting (2DGS) primitive, which provides stronger anisotropy and higher geometric precision. By incorporating a surface continuity prior and a forced alpha blending strategy, SurfSplat reconstructs coherent geometry together with faithful textures. Furthermore, we introduce High-Resolution Rendering Consistency (HRRC), a new evaluation metric designed to evaluate high-resolution reconstruction quality. Extensive experiments on RealEstate10K, DL3DV, and ScanNet demonstrate that SurfSplat consistently outperforms prior methods on both standard metrics and HRRC, establishing a robust solution for high-fidelity 3D reconstruction from sparse inputs. Project page: https://hebing-sjtu.github.io/SurfSplat-website/

Problem

• 3D reconstruction
• sparse images
• surface continuity
• Gaussian Splatting
• geometric accuracy

Innovation

• 2D Gaussian Splatting
• surface continuity prior
• feedforward 3D reconstruction
• alpha blending
• high-resolution rendering consistency