AI Paper Atlas

Research map / 3D vision / Face and shape

Mesh R-CNN

Georgia Gkioxari, Jitendra Malik, Justin Johnson

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 489 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 voxel branch with cubify and mesh refinement instead of sphere-initialized refinement (ablation)Mesh R-CNN · Pix3D S1APmesh: 40.5 -> 55.4Improved
add voxel branch (arbitrary topology) vs sphere-init on objects with holes (ablation)Mesh R-CNN · ShapeNet holes test set (Pretty)Chamfer: 0.196 -> 0.171Improved
add voxel branch vs sphere-init on the full ShapeNet test set (ablation)Mesh R-CNN · ShapeNet full test set (Best)Chamfer: 0.132 -> 0.133No clear effect
add mesh refinement branch to voxel predictions (ablation)Voxel-Only · Pix3D S1APmesh: 6.8 -> 55.4Improved
add mesh subdivision (Pixel2Mesh+ vs Sphere-Init) (ablation)sphere-based mesh refinement · ShapeNet full test set (Best)Chamfer: 0.132 -> 0.132No clear effect
use deeper residual refinement branch instead of lighter nonresidual one (ablation)Mesh R-CNN · ShapeNet full test set (Best)Chamfer: 0.133 -> 0.133No clear effect
add edge length regularizer (Pretty vs Best) (ablation)Mesh R-CNN · ShapeNet (protocol of Pixel2Mesh)Chamfer: 0.306 -> 0.391Hurt
initialize from COCO instead of ImageNet (ablation)Mesh R-CNN · Pix3D S1APmesh: 52.9 -> 55.4Improved
use three refinement stages instead of one (ablation)Mesh R-CNN · Pix3D S1APmesh: 52.4 -> 55.4Improved
use three refinement stages instead of two (ablation)Mesh R-CNN · Pix3D S1APmesh: 54.5 -> 55.4Improved
use Mesh R-CNN instead of Sphere-Init on unseen shapes (ablation)Mesh R-CNN · Pix3D S2 (disjoint models)APmesh: 24.8 -> 28.7Improved
evaluate on ground-truth regions instead of detected boxesMesh R-CNN · Pix3D S1APmesh: 55.4 -> 49.1Hurt

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