AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Canonical View Representation for 3D Shape Recognition With Arbitrary Views

Xin Wei, Yifei Gong, Fudong Wang, Xing Sun, Jian Sun

ICCV 2021 · 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 image-level feature encoder (CNN+Transformer) instead of CNN with max-pooling (ablation)MVCNN-style baseline · ModelNet40 (arbitrary views)per-instance accuracy (%): 83.20 -> 85.12Improved
add image-level feature encoder (CNN+Transformer) (ablation)MVCNN-style baseline · ModelNet40 (arbitrary views)per-class accuracy (%): 78.86 -> 81.78Improved
add canonical view representation module (ablation)Full model · ModelNet40 (arbitrary views)per-instance accuracy (%): 85.04 -> 86.91Improved
use optimal transport rather than Transformer decoder in CVR (ablation)Full model · ModelNet40 (arbitrary views)per-instance accuracy (%): 83.29 -> 86.91Improved
use optimal transport rather than Transformer decoder in CVR (ablation)Full model · ModelNet40 (arbitrary views)per-class accuracy (%): 79.97 -> 84.01Improved
add canonical view feature separation loss (ablation)Full model · ModelNet40 (arbitrary views)per-instance accuracy (%): 85.32 -> 86.91Improved
add canonical view feature separation loss (ablation)Full model · ModelNet40 (arbitrary views)per-class accuracy (%): 82.28 -> 84.01Improved
add canonical view aggregator (ablation)Full model · ModelNet40 (arbitrary views)per-instance accuracy (%): 85.75 -> 86.91Improved
add canonical view aggregator (ablation)Full model · ModelNet40 (arbitrary views)per-class accuracy (%): 82.04 -> 84.01Improved
use number of reference views M=8 rather than 4 (ablation)Full model · ModelNet40 (arbitrary views)per-instance accuracy (%): 85.69 -> 86.91Improved
use number of reference views M=8 rather than 16 (ablation)Full model · ModelNet40 (arbitrary views)per-instance accuracy (%): 86.22 -> 86.91Improved
use canonical view representation instead of MVCNN-M/GVCNN-M under object rotationProposed vs MVCNN-M · ModelNet40 (rotated)per-instance accuracy (%): 88.17 -> 92.22Improved

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