AI Paper Atlas

Research map / Point clouds / Shape and surface completion

PUNO: A Neural Operator Framework for Point Cloud Upsampling

Zijian Xiao, Yining Xu, Yingjie Huang, Li Yao

AAAI 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
add vertex displacement network before manifold mapping (ablation)PUNO · ShapeNet 16xP2F avg: 7.892 -> 2.04Improved
add vertex displacement network (ablation)PUNO · ShapeNet 16xCD: 0.615 -> 0.524Improved
add neural kernel integral operator on top of data-space fitting (ablation)PUNO · ShapeNet 16xP2F avg: 3.632 -> 2.04Improved
use global Galerkin attention instead of kNN local operator (ablation)PUNO · ShapeNet 16xHD: 6.192 -> 5.446Improved
use Galerkin attention instead of softmax attention (ablation)PUNO · inference memory at 8xGiB: 27.6 GiB -> 2.0 GiBImproved
use quadratic instead of linear patch mapping (ablation)PUNO · ShapeNet 16xP2F avg: 2.498 -> 2.04Improved
use quadratic instead of cubic patch mapping (ablation)PUNO · ShapeNet 16xP2F avg: 2.732 -> 2.04Improved
use PUNO instead of RepKPUpoint cloud upsampling · ShapeNet 16xP2F avg: 1.275 vs 2.04Hurt
use PUNO instead of RepKPUpoint cloud upsampling · ShapeNet 16xCD: 0.592 -> 0.524Improved
use PUNO instead of baselines under Gaussian noise std 0.01point cloud upsampling · ShapeNet noisyP2F mean: 6.199 -> 4.004Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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