AI Paper Atlas

Research map / 3D vision / Face and shape

Enhancing 2D Representation via Adjacent Views for 3D Shape Retrieval

Cheng Xu, Zhaoqun Li, Qiang Qiu, Biao Leng, Jingfei Jiang

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 22 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 center loss to softmax loss (ablation)NCENet Parallel · ModelNet40mAP: 83.47% -> 86.27%Improved
add center loss to softmax loss (ablation)NCENet Serial · ModelNet40mAP: 83.04% -> 87.05%Improved
use correlation unit instead of max pooling of adjacent features (ablation)NCENet Parallel · ModelNet40mAP: 84.12% -> 86.27%Improved
use correlation unit instead of average pooling of adjacent features (ablation)NCENet Serial · ModelNet40mAP: 81.29% -> 87.05%Improved
use serial instead of parallel enhanced structure (ablation)NCENet · ModelNet40mAP: 86.27% -> 87.05%Improved
use serial instead of parallel enhanced structure (ablation)NCENet · ShapeNetCore55 perturbed (micro)mAP: 89.6 -> 89.0Hurt
increase number of center views from 1 to 4 at test (ablation)Our-Parallel · ModelNet40mAP: 0.819 -> 0.867Improved
increase number of center views from 6 to 10 (ablation)Our-Serial · ModelNet40mAP: 0.871 -> 0.868No clear effect
increase number of neighbor views from 1 to 8 (ablation)Our-Serial · ModelNet40mAP: 0.853 -> 0.871Improved
increase number of neighbor views from 1 to 8 (ablation)Our-Parallel · ModelNet40mAP: 0.852 -> 0.863Improved
replace MVCNN max pooling with Our-Serial enhancement on same GoogLeNet-bn (ablation)NCENet · ModelNet40mAP: 85.49% -> 87.05%Improved
occlude all neighboring views to 80% levelOur-Parallel · ModelNet40mAP: decreases slightly by 2.55%Hurt

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