AI Paper Atlas

Research map / 3D vision / Face and shape

LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies

Dominic Roberts, Ara Danielyan, Hang Chu, Mani Golparvar-Fard, David Forsyth

ICCV 2021 · 3D vision › Face and shape · approach: 3D shape generative modeling · 10 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 per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Table conditional samplingsampling time (s): 3.0 -> 0.04Improved
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Chair conditional samplingsampling time (s): 0.67 -> 0.05Improved
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Table conditional D=1FPD: 85.5 -> 44.7Improved
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Chair conditional D=1structural diversity: 73.5 -> 69.3Hurt
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Storage conditional D=2FPD: 79.2 -> 88.1Hurt
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Table unconditional (bounding boxes)FPD: 103.2 -> 36.3Improved
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Chair unconditional (bounding boxes)FPD: 57.0 -> 39.3Improved
model all depths probabilistically instead of only depth <=1 (ablation)LSD-StructureNet · PartNet Chairquality: 76.5 -> 47.2Improved
model all depths probabilistically instead of only depth <=3 (ablation)LSD-StructureNet · PartNet Chaircoverage: 32.1 -> 25.4Improved
add encoder and decoder LSTMs (ablation)LSD-StructureNet · PartNet Chaircoverage: 73.5 -> 25.4Improved
add per-depth latent spaces (LSD) to StructureNetStructureNet · PartNet Chair vs PQ-Netquality: 116.5 -> 47.2Improved
use LSD-StructureNet instead of PQ-NetPQ-Net · PartNet ChairFPD: 28.9 -> 39.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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