AI Paper Atlas

Research map / Point clouds / Point cloud classification

Language Conditioned Spatial Relation Reasoning for 3D Object Grounding

Shizhe Chen, Pierre-Louis Guhur, Makarand Tapaswi, Cordelia Schmid, Ivan Laptev

NeurIPS 2022 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 14 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 language-conditioned spatial self-attention using pairwise distances and orientationsViL3DRel · Nr3D, ground-truth object proposalsaccuracy: 55.1 -> 64.4Improved
add language-conditioned spatial self-attention using pairwise distances and orientationsViL3DRel · Sr3D, ground-truth object proposalsaccuracy: 64.5 -> 72.8Improved
add color information (ablation)Nr3D teacher baseline R1 · Nr3D, ground-truth object labelsaccuracy: 53.5 -> 55.1Improved
add rotation augmentation (ablation)Nr3D teacher baseline R2 · Nr3D, ground-truth object labelsaccuracy: 55.1 -> 62.4Improved
add pairwise distance features (ablation)ViL3DRel spatial attention · Nr3D, distance-only sentencesaccuracy: 63.5 -> 72.6Improved
add pairwise orientation features (ablation)ViL3DRel spatial attention · Nr3D, orientation-only sentencesaccuracy: 61.2 -> 71.7Improved
replace multi-head spatial attention with single-head spatial attention (ablation)ViL3DRel · Nr3D, ground-truth object labelsaccuracy: 74.4 -> 67.7Hurt
replace sigsoftmax with bias-mode positional encoding (ablation)ViL3DRel · Nr3D, ground-truth object labelsaccuracy: 74.4 -> 55.4Hurt
replace sigsoftmax with contextual-mode positional encoding (ablation)ViL3DRel · Nr3D, ground-truth object labelsaccuracy: 74.4 -> 56.4Hurt
replace object-center coordinates with bottom-center coordinates (ablation)ViL3DRel spatial feature computation · Nr3Daccuracy: 74.4 -> 74.4No clear effect
replace designed pairwise spatial features with bounding-box pairs and an MLP (ablation)ViL3DRel spatial feature computation · Nr3Daccuracy: 74.4 -> 57.4Hurt
increase BERT encoder depth from 3 to 12 layers (ablation)ViL3DRel text encoder · Nr3Daccuracy: 74.4 -> 52.3Hurt

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