AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks

Yu-Qi Yang, Peng-Shuai Wang, Yang Liu

ICCV 2021 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 4 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
switch nearest to trilinear interpolation (zero padding) (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 40.5 -> 41.5Improved
add interpolation-aware padding with trilinear interpolation (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 41.5 -> 42.3Improved
use octree padding instead of zero padding (trilinear) (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 41.5 -> 41.4No clear effect
use 1-ring padding instead of interpolation-aware padding (trilinear) (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 42.3 -> 42.7Improved
add interpolation-aware padding without interpolation (nearest) (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 40.5 -> 40.6Improved
add 1-ring padding without interpolation (nearest) (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 40.5 -> 40.9Improved
add octree padding without interpolation (nearest) (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 64^3mIoU: 40.5 -> 40.0Hurt
coarser output resolution 32^3 with Interp+Linear vs Zero+Near (ablation)sparse U-Net · PartNet fine-grained (4 categories), output 32^3mIoU: 38.1 -> 40.1Improved
apply interpolation-aware padding at all resolution levels (ablation)sparse U-Net · PartNet (4 categories), state-of-the-artmIoU: 42.3 -> 42.7Improved
use interpolation-aware padding and trilinear interpolationMinkNet · ScanNet val semantic segmentation (S_out 8cm)mIoU: 70.4 -> 72.4Improved
use interpolation-aware padding and trilinear interpolationVoteNet with MinkNet backbone · ScanNet val detectionmAP@0.5: 37.9 -> 41.4Improved
replace PointNet++ backbone with sparse U-NetVoteNet · ScanNet val detectionmAP@0.5: 34.7 -> 37.9Improved

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