AI Paper Atlas

Research map / Point clouds / Shape and surface completion

VKSR: Scalable Kernel Surface Reconstruction Using Vecchia's Approximation

Maximilian Weiherer, Chukwudi Williams Umah, Bernhard Egger

ECCV 2026 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace low-rank Nystrom approximation with Vecchia local approximationkernel surface reconstruction · ShapeNet dense (100K points)runtime (s): 47.91 -> 0.77Improved
replace low-rank Nystrom approximation with Vecchia local approximationMatern kernel method · ShapeNet dense (100K points)Chamfer distance (x10^3): 2.25 -> 2.19Improved
replace low-rank approximation with Vecchia on sparse inputskernel methods · ShapeNet sparse (1K points)Chamfer distance (x10^3): 3.90 -> 3.95Hurt
use VKSR instead of SPSR on sparse inputsSPSR · ShapeNet sparse (1K points)Chamfer distance (x10^3): 4.36 -> 3.95Improved
use VKSR instead of SPSR on dense inputsSPSR · ShapeNet dense (100K points)Chamfer distance (x10^3): 2.04 -> 2.19Hurt
use VKSR instead of NS on noisy incomplete scansNS · Surface Reconstruction Benchmark (Anchor)runtime (s): 308.86 -> 13.79Improved
use VKSR instead of SPSR on noisy incomplete scansSPSR · Surface Reconstruction Benchmark (Anchor)Chamfer distance: 0.30 -> 0.24Improved
use approximate nearest neighbor search (ablation)VKSR · Stanford 3D Scanning Repositoryruntime: Lucy 1809.79 -> 80.18 sImproved
increase number of neighbors k (ablation)VKSR · ShapeNetChamfer distance (x10^3): 2.25 -> 2.15Improved
use VKSR instead of SPSR on ScanNet scenesSPSR · ScanNet (20 scenes)Chamfer distance: 0.02 -> 0.02No clear effect
use VKSR instead of chunked subdivision of NSNS · Stanford Lucy (14M points)Chamfer distance: 3.13 -> 0.81Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy