AI Paper Atlas

Research map / 3D vision / Face and shape

Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning

Aditya Sanghi

ECCV 2020 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 95 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
use embeddings from layer 6 instead of layer 7 on aligned data (ablation)Info3D PointNet · ModelNet40 aligned clusteringAMI: 0.401 ± 0.005 -> 0.633 ± 0.002Improved
use embeddings from layer 7 instead of layer 6 on unaligned data (ablation)Info3D PointNet · ModelNet40 unaligned clusteringAMI: 0.404 ± 0.002 -> 0.496 ± 0.004Improved
use cosine-distance chunk as second view instead of translation (ablation)Info3D PointNet · ModelNet40 aligned clusteringAMI: 0.633 ± 0.002 -> 0.677 ± 0.002Improved
use cosine chunk rather than axis chopped chunk (ablation)Info3D PointNet · ModelNet40 aligned clusteringAMI: 0.660 ± 0.002 -> 0.677 ± 0.002Improved
use axis chopped chunk instead of translation (ablation)Info3D PointNet · ModelNet40 transferaccuracy: 87.8 -> 89.8Improved
use axis chopped chunk rather than cosine distance chunk (ablation)Info3D DGCNN · ModelNet40 transferaccuracy: 90.8 -> 91.6Improved
replace PointNet with DGCNN encoder (ablation)Info3D axis chopped chunk · ModelNet40 transferaccuracy: 89.8 -> 91.6Improved
add translation to rotation SO(3) + uniform scale (ablation)Info3D unaligned · ModelNet40 unaligned clusteringAMI: 0.313 ± 0.005 -> 0.500 ± 0.001Improved
add uniform scale to rotation SO(3) + translate (ablation)Info3D unaligned · ModelNet40 unaligned clusteringAMI: 0.496 ± 0.004 -> 0.500 ± 0.001No clear effect
add random scale to rotation SO(3) + translate (ablation)Info3D unaligned · ModelNet40 unaligned clusteringAMI: 0.496 ± 0.004 -> 0.485 ± 0.004No clear effect
chunk size 512 instead of 128 (ablation)Info3D chunks · ModelNet40 aligned clusteringAMI: 0.653 ± 0.002 -> 0.677 ± 0.002Improved
chunk size 512 instead of 768 (ablation)Info3D chunks · ModelNet40 aligned clusteringAMI: 0.658 ± 0.008 -> 0.677 ± 0.002Improved

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