AI Paper Atlas

Research map / Point clouds / Shape and surface completion

GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds

Chao Chen, Yu-Shen Liu, Zhizhong Han

ICCV 2023 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 27 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 gradient-consistency loss to pulling loss (ablation)GridPull · FAMOUSCD_L2 x100: 0.184 -> 0.126Improved
add total variation continuity loss on grid distances (ablation)GridPull · FAMOUSCD_L2 x100: 0.126 -> 0.056Improved
add surface loss on input points (ablation)GridPull · FAMOUSCD_L2 x100: 0.056 -> 0.040Improved
use geometric sphere initialization instead of random (ablation)GridPull · FAMOUSCD_L2 x100: 0.155 -> 0.040Improved
add Eikonal constraint on gradients (ablation)GridPull · FAMOUSCD_L2 x100: 0.040 -> 0.054Hurt
restrict pulling loss to narrow bandwidth near surface (M1=3) instead of all grids (ablation)GridPull · FAMOUStime: 628s -> 84s; CD 0.043 -> 0.040Improved
increase TV bandwidth M2 from 2 to 14 (ablation)GridPull · FAMOUSCD_L2 x100: 0.079 -> 0.040Improved
increase TV bandwidth beyond 14 to all grids (ablation)GridPull · FAMOUSCD_L2 x100: 0.040 -> 0.040; time 84s -> 101sNo clear effect
increase grid resolution R from 256 to 512 (ablation)GridPull · FAMOUSCD_L2 x100 and time: 0.040 -> 0.035; 201s -> 645sMixed
add ground-truth normal supervision (ablation)GridPull · FAMOUSCD_L2: 0.0401 -> 0.0403No clear effect
replace neural network with discrete grid SDF (ablation)NeuralPull-style pulling · FAMOUSCD_L2 x100: NeuralPull+L_grad+L_Surface 0.203 vs GridPull 0.040; time 554s vs 84sImproved
scale number of input points from 10K to 1000K (ablation)GridPull · FAMOUStime: 82s -> 90sNo clear effect

Later papers that compared with this method

2 later accepted papers report GridPull as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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