G$^2$SR: Geometric Methods for Fast and Memory-Efficient Gaussian-based Surface Reconstruction

Researchers propose G2SR, a geometric method for fast and memory-efficient Gaussian-based surface reconstruction from few RGB views. It uses a lightweight neural frontend for 2D splat detection and an analytic backend for 3D triangulation, achieving 69-89 reconstructions per second with 5-107x less GPU memory than end-to-end methods while matching geometric accuracy.

arXiv:2607.14470v1 Announce Type: new Abstract: Few-view surface reconstruction recovers the visible surfaces of a scene from a few posed RGB images, providing the 3D models that robots need to explore and interact online. On mobile platforms, the reconstruction must be fast and geometrically accurate while keeping a small memory footprint to ensure safe and efficient operation. 3D Gaussian Splatting 3DGS offers a high-fidelity scene representation, but building it from a few views is ill-posed, as many distinct surfaces reproduce the same images, making traditional photometric methods prone to "floater" artifacts. End-to-end methods resolve the ambiguity by regressing splats with large, usually Transformer-based, networks that require heavy compute and memory while generalizing poorly to new scenes. We propose G2SR, which exploits a well-posed core of the task: given cross-view 2D splat correspondences, 3D splats follow analytically from multi-view geometry. G2SR employs a lightweight neural frontend to detect and track 2D Gaussian splats on the image plane and an analytic backend to triangulate each into a metric-scale 3D splat. On ScanNet, Replica, and DTU, G2SR matches or exceeds the geometric accuracy of state-of-the-art end-to-end methods while running at 69-89 reconstructions per second within 203 MB of GPU memory 5-107x less for 2- and 3-view inputs at 384 x 512 resolution, offering a practical path to online Gaussian-based surface reconstruction.