Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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/

Bing He, Jingnan Gao, Yunuo Chen, Ning Cao, Gang Chen, Zhengxue Cheng, Li Song, Wenjun Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisRealEstate10K
PSNR27.537
116
Novel View SynthesisDTU
PSNR15.544
100
Novel View SynthesisDL3DV
PSNR27.384
61
Novel View SynthesisScanNet
PSNR20.305
58
Novel View SynthesisACID
PSNR28.336
51
Novel View SynthesisACID HRRC
PSNR26.868
10
Novel View SynthesisAverage (Scannet, DL3DV, DTU)
PSNR21.078
6
Novel View SynthesisDL3DV high-resolution
PSNR24.411
6
Showing 8 of 8 rows

Other info

Follow for update