AI Paper Atlas

Research map / 3D vision / Face and shape

Directionally Convolutional Networks for 3D Shape Segmentation

Haotian Xu, Ming Dong, Zichun Zhong

ICCV 2017 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 54 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
use directional (curvature-ordered) convolution instead of non-directional convolution with shuffled faces (ablation)DCN · Human shapes (12 train, 8 test)train and test loglossImproved
fuse the two streams late by element-wise product instead of at penultimate layers (ablation)two-stream DCN · PSB + COSEG small categories (average)segmentation accuracy: 0.9496 -> 0.9522Improved
late fusion instead of early fusion (ablation)two-stream DCN · Chairs (400 meshes)segmentation accuracy: 0.9518 -> 0.9573Improved
late fusion instead of early fusion (ablation)two-stream DCN · Vases (300 meshes)segmentation accuracy: 0.9034 -> 0.9086Improved
late fusion instead of early fusion (ablation)two-stream DCN · Mech categorysegmentation accuracy: 0.9698 -> 0.9660Hurt
late fusion instead of early fusion (ablation)two-stream DCN · Candelabra categorysegmentation accuracy: 0.9603 -> 0.9546Hurt
add global distance-histogram stream to the local DCN stream (ablation)DCN · t-SNE of Teddy and Ant feature mapscluster separationImproved
DCN two-stream versus Guo et al. on Bustmesh segmentation · Bustsegmentation accuracy: 0.6984 -> 0.7898Improved
DCN two-stream versus ShapePFCN on Mechmesh segmentation · Mechsegmentation accuracy: 0.9790 -> 0.9660Hurt
DCN two-stream versus Guo et al. on Chairsmesh segmentation · Chairs (400 meshes)segmentation accuracy: 0.9252 -> 0.9573Improved

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