AI Paper Atlas

Research map / 3D vision / 3D generation

Learning Relationships for Multi-View 3D Object Recognition

Ze Yang, Liwei Wang

ICCV 2019 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 182 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 Integrating block instead of view pooling (ablation)Relation Network · ModelNet40instance accuracy (%): 93.8 -> 94.3Improved
add a Reinforcing block after conv5 (ablation)Relation Network · ModelNet40instance accuracy (%): 93.7 -> 94.3Improved
place the Reinforcing block after conv5 instead of conv2 (ablation)Relation Network · ModelNet40instance accuracy (%): 93.9 -> 94.3Improved
place the Reinforcing block after conv5 instead of conv3 (ablation)Relation Network · ModelNet40instance accuracy (%): 93.7 -> 94.3Improved
place the Reinforcing block after conv5 instead of conv4 (ablation)Relation Network · ModelNet40instance accuracy (%): 94.0 -> 94.3Improved
add a second Reinforcing block after conv4 (ablation)Relation Network · ModelNet40instance accuracy (%): 94.3 -> 93.9No clear effect
add Reinforcing blocks after conv3,4,5 (ablation)Relation Network · ModelNet40instance accuracy (%): 94.3 -> 94.2No clear effect
add Reinforcing blocks after conv2,3,4,5 (ablation)Relation Network · ModelNet40instance accuracy (%): 94.3 -> 93.8Hurt
add low-rank Mahalanobis metric learning (ablation)Relation Network · ModelNet40 retrievalmAP: 82.7 -> 86.7Improved
increase number of views from 6 to 12Relation Network · ModelNet40instance accuracy (%): 94.1 -> 94.3Improved
increase number of views from 6 to 12MHBN · ModelNet40instance accuracy (%): 94.1 -> 93.4Hurt
increase number of views from 6 to 12MVCNN · ModelNet40instance accuracy (%): 92.0 -> 91.5Hurt

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