SOURCE-LINKED INTELLIGENCE

CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstruction

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

We present CADSplat, a framework that reconstructs photorealistic, geometrically accurate digital twins from sparse ($<15$ views), wide-baseline posed images of an object by regularizing 3D Gaussian Splatting (3DGS) with an explicit CAD shape prior. Using such a prior requires finding a CAD model whose shape resembles the object depicted in the images and determining the pose of each camera relative to the object. We obtain both by matching segmented object silhouettes against silhouettes rendered from a CAD library and keeping the camera-to-object poses of the best-matching model. We then anc

Read original source ↗ Open in workspace

recordType

paper

region

Global