AI Paper Atlas

Research map / Point clouds / Point cloud classification

OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

Minghua Liu, Ruoxi Shi, Kaiming Kuang, Yinhao Zhu, Xuanlin Li, Shizhong Han, Hong Cai, Fatih Porikli, Hao Su

NeurIPS 2023 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 39 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
train on the ensembled 4-dataset shapes instead of ShapeNet only (ablation)OpenShape-PointBERT · Objaverse-LVIS zero-shottop-1 accuracy (%): 10.8 -> 46.8Improved
OpenShape training recipe (text enrichment, backbone scaling) instead of ULIP on same ensembled dataPointBERT · Objaverse-LVIS zero-shottop-1 accuracy (%): 26.8 -> 46.8Improved
include Objaverse-LVIS shapes in training (Ensembled vs no LVIS)OpenShape-PointBERT · ModelNet40 zero-shottop-1 accuracy (%): 85.3 -> 84.4Hurt
add text filtering and enrichment (captioning, retrieval) (ablation)OpenShape SparseConv/PointBERT · Objaverse-LVIS and ModelNet40 zero-shottop-1 accuracyImproved
scale up backbone parameters (ablation)3D backbones on ensembled dataset · Objaverse-LVIS zero-shottop-1 accuracyImproved
scale PointBERT from 32.3M to 72.1M parameters (ablation)PointBERT · all benchmarkszero-shot accuracyHurt
add hard negative mining (ablation)OpenShape-SparseConv · Objaverse-LVIS and ModelNet40 zero-shottop-1 accuracyImproved
fine-tune CLIP text encoder for one epoch (ablation)OpenShape-PointBERT · benchmarkszero-shot accuracyNo clear effect
remove RGB color, use xyz only (ablation)OpenShape · zero-shot classificationtop-1 accuracyNo clear effect
add both image captioning and text retrieval (ablation)OpenShape · Objaverse-LVIS zero-shottop-1 accuracyImproved

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