AI Paper Atlas

Research map / 3D vision / 3D generation

Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation

Linlong Fan, Ye Huang, Yanqi Ge, Wen Li, Lixin Duan

ECCV 2024 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 1 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 part-aware loss L_awe (ablation)PANet · ScanObjectNN rotatedaccuracy: +2.40% / +1.76%Improved
add cross-view association (CVA) module (ablation)PANet · ScanObjectNN rotatedaccuracy: +0.69% ins., +1.23% classImproved
increase number of views from 1 to 20 (ablation)PANet ResNet50 · ScanObjectNN rotatedaccuracy: 67.07% -> 86.62%Improved
use stronger backbone ResNet50 instead of ResNet18 (ablation)PANet · ScanObjectNN rotated, 20 viewsaccuracy: 82.85% -> 86.62%Improved
furthest point sampling instead of random view sampling (ablation)PANet · ModelNet40 / ScanObjectNNaccuracy: 97.53% vs 97.41% (ModelNet aligned ins.)No clear effect
increase attention maps M from 16 to 64 (ablation)PANet · ScanObjectNN rotatedinstance accuracy: 86.28% -> 87.31%Improved
increase attention maps from 64 to 128 (ablation)PANet · ScanObjectNN rotatedinstance accuracy: 87.31% -> 87.14%No clear effect
increase global part tokens from 16 to 32 (ablation)PANet · ScanObjectNN rotatedinstance accuracy: 87.31% -> 86.31%Hurt
use multiple parts (L=16) instead of a single part (ablation)PANet · ScanObjectNN rotatedinstance accuracy: 86.28% -> 87.31%Improved
switch from fixed to arbitrary viewsPANet vs CVR · ScanObjectNN rotatedinstance accuracy: PANet 87.82% -> 86.45%; CVR 85.59% -> 71.36%Mixed

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