AI Paper Atlas

Research map / 3D vision / Face and shape

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

Di Liu, Anastasis Stathopoulos, Qilong Zhangli, Yunhe Gao, Dimitris N. Metaxas

NeurIPS 2023 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 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
LEPARD versus Hi-LASSIE keypoint transferLEPARD · Pascal-Part Horse keypoint transferPCK@0.05: 59.6 -> 61.0Improved
LEPARD versus LASSIE keypoint transferLEPARD · LASSIE Kangaroo keypoint transferPCK@0.05: 31.5 -> 35.4Improved
LEPARD versus LASSIE keypoint transferLEPARD · LASSIE Penguin keypoint transferPCK@0.05: 40.6 -> 44.6Improved
LEPARD versus Hi-LASSIE keypoint transferLEPARD · LASSIE Penguin keypoint transferPCK@0.05: 44.4 -> 44.6Improved
LEPARD versus Hi-LASSIE overall IoULEPARD · Pascal-Part Horseoverall IoU: 83.4 -> 83.7Improved
LEPARD versus Hi-LASSIE part IoULEPARD · Pascal-Part HorsePart IoU: 39.0 -> 39.5Improved
LEPARD versus Hi-LASSIE part IoULEPARD · Pascal-Part CowPart IoU: 35.3 -> 35.4No clear effect
LEPARD versus Hi-LASSIE part transferLEPARD · Pascal-Part CowPCP: 77.8 -> 77.6Hurt
LEPARD versus Hi-LASSIE part IoULEPARD · Pascal-Part SheepPart IoU: 43.4 -> 43.6No clear effect
add local deformations of primitives (ablation)LEPARD · Pascal-Part and LASSIEvisual reconstruction qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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