Photogrammetry to Surface-Aligned Mesh

Reconstructs a real-world object from ordinary photos or a video walkthrough: Structure-from-Motion recovers camera poses, Gaussian Splatting trains a photoreal radiance field on those poses, then a surface-extraction pass converts the volumetric splats into a clean, editable, UV-textured mesh.

Properties

family: 3d
modality: multi-view photos/video -> camera poses -> 3D Gaussian splats -> textured surface mesh
whyMultiModel: COLMAP solves camera geometry but produces no renderable surface; 3D Gaussian Splatting renders photoreal views but is a volumetric point representation with no faces, UVs, or watertight geometry; SuGaR is a distinct surface-alignment and Poisson-extraction stage needed to pull an editable mesh out of the splats. Each stage solves a problem the others cannot.
steps: [object Object], [object Object], [object Object]
controls: capture density/overlap, COLMAP matcher settings, 3DGS training iterations and densification thresholds, SuGaR regularization type, target mesh face count, Poisson depth
exampleStack: COLMAP -> 3D Gaussian Splatting -> SuGaR -> Blender/Unreal/Unity import
useCases: [Photogrammetry asset capture from a phone video][Location scanning for virtual production][Cultural heritage digitization with editable, engine-ready output][AR/VR asset creation from real objects]
pitfalls: Poor image overlap or motion blur makes COLMAP fail pose estimation, propagating floaters and fractured geometry; reflective/transparent surfaces break both SfM matching and Gaussian convergence; mesh extraction can lose fine detail present in the raw splats.
source: SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction (CVPR 2024)

Provenance

Source: https://github.com/Anttwo/SuGaR

Properties

family

modality

multi-view photos/video -> camera poses -> 3D Gaussian splats -> textured surface mesh

whyMultiModel

COLMAP solves camera geometry but produces no renderable surface; 3D Gaussian Splatting renders photoreal views but is a volumetric point representation with no faces, UVs, or watertight geometry; SuGaR is a distinct surface-alignment and Poisson-extraction stage needed to pull an editable mesh out of the splats. Each stage solves a problem the others cannot.

steps

[object Object], [object Object], [object Object]

controls

capture density/overlap, COLMAP matcher settings, 3DGS training iterations and densification thresholds, SuGaR regularization type, target mesh face count, Poisson depth

exampleStack

COLMAP -> 3D Gaussian Splatting -> SuGaR -> Blender/Unreal/Unity import

useCases

[Photogrammetry asset capture from a phone video][Location scanning for virtual production][Cultural heritage digitization with editable, engine-ready output][AR/VR asset creation from real objects]

pitfalls

Poor image overlap or motion blur makes COLMAP fail pose estimation, propagating floaters and fractured geometry; reflective/transparent surfaces break both SfM matching and Gaussian convergence; mesh extraction can lose fine detail present in the raw splats.

source

SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction (CVPR 2024)