AI Paper Atlas

Research map / Point clouds / Shape and surface completion

OscuFit: Learning to Fit Osculating Implicit Quadrics for Point Clouds

Rao Fu, Qian Li, Liang Yu, Jianmin Zheng

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 L_n, L_g, L_m on top of L_f (all four losses) (ablation)OscuFit · ABC-Diff averageNormal RMSE (x10): 1.30 -> 1.26Improved
add L_n, L_g, L_m on top of L_f (all four losses) (ablation)OscuFit · ABC-Diff averageGaussian curvature RMSE: 0.33 -> 0.27Improved
add L_n, L_g, L_m on top of L_f (all four losses) (ablation)OscuFit · ABC-Diff averageMean curvature RMSE: 0.80 -> 0.69Improved
add fitting loss L_f to normal and curvature losses (ablation)OscuFit · ABC-Diff averageNormal RMSE (x10): 1.35 -> 1.26Improved
supervise with L_f instead of L_n only (ablation)OscuFit · ABC-Diff averageNormal RMSE (x10): 1.39 -> 1.30Improved
supervise with L_f instead of L_n only (ablation)OscuFit · ABC-Diff averageMean curvature RMSE: 0.96 -> 0.80Improved
supervise with L_f instead of L_n only (ablation)OscuFit · ABC-Diff averageGaussian curvature RMSE: 0.31 -> 0.33Hurt
increase patch size K from 128 to 256 (ablation)OscuFit · ABC-Diff averageNormal RMSE (x10): 1.36 -> 1.26Improved
increase patch size K from 64 to 256 (ablation)OscuFit · ABC-Diff averageNormal RMSE (x10): 1.88 -> 1.26Improved
increase patch size K from 64 to 256 (ablation)OscuFit · ABC-Diff averageGaussian curvature RMSE: 0.62 -> 0.27Improved
use OscuFit instead of GraphFitGraphFit · ABC-Diff cleanNormal RMSE (x10): 0.55 -> 0.45Improved
use OscuFit instead of GraphFitGraphFit · ABC-Diff 1.2% noiseMean curvature RMSE: 0.90 -> 0.82Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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