AI Paper Atlas

Research map / Point clouds / Point cloud classification

Neural Implicit Embedding for Point Cloud Analysis

Kent Fujiwara, Taiichi Hashimoto

CVPR 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 42 citations (OpenAlex)

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
Concatenate point coordinates and normals to the ELM-weight representation (ablation)Neural Implicit Embedding · ModelNet 10classification accuracy (%): 95.7 -> 96.7Improved
Concatenate point coordinates and normals to the ELM-weight representation (ablation)Neural Implicit Embedding · ModelNet 40classification accuracy (%): 92.2 -> 93.2Improved
Reduce the original point-cloud size from 2048 to 1024 points (ablation)Neural Implicit Embedding · ModelNet 40classification accuracy (%): 93.2 -> 92.7Hurt
Reduce the original point-cloud size from 2048 to 512 points (ablation)Neural Implicit Embedding · ModelNet 40classification accuracy (%): 93.2 -> 91.1Hurt
Reduce the original point-cloud size from 2048 to 256 points (ablation)Neural Implicit Embedding · ModelNet 40classification accuracy (%): 93.2 -> 90.1Hurt
Add noise to the representation (ablation)Neural Implicit Embedding · ModelNet classificationclassification accuracyHurt
Use canonical projection to align distance fields under rotationNeural Implicit Embedding · ModelNet 40 with test-time rotation perturbationsclassification accuracy (%): 93.2 -> 81.8 at maximum rotation angle πImproved
Use the scale-invariant representation under rotation and scale perturbationNeural Implicit Embedding · ModelNet 40, rotation and scale perturbationclassification accuracy (%): 83.9Improved
Use Neural Implicit Embedding instead of PointNet++ for ShapeNetPart segmentationPoint-cloud segmentation · ShapeNetPartmean IoU: 85.1 -> 85.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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