AI Paper Atlas

Research map / 3D vision / Human pose estimation

PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects

Jiayi Liu, Ali Mahdavi-Amiri, Manolis Savva

ICCV 2023 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 55 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 mobile-field regularization L_prob (one field per ray) (ablation)PARIS · PartNet-MobilityCD-m (movable part): 23.32 -> 5.38Improved
add L_prob regularization (ablation)PARIS · PartNet-MobilityPSNR: 36.64 -> 37.73Improved
use virtual canonical state t*=0.5 instead of t*=0 for the mobile field (ablation)PARIS · PartNet-MobilityCD-m (movable part): 74.34 -> 3.06Improved
canonical state choice for appearance quality (ablation)PARIS · PartNet-MobilityPSNR / SSIM: 37.62 -> 37.73 PSNR; SSIM 0.992 bothNo clear effect
increase number of input views from 4 to 64 (ablation)PARIS · PartNet-MobilityCD-w and joint axis error: CD-w 170.116 (4 views) -> 3.94 (64 views)Improved
image-based self-supervised PARIS instead of point-cloud Ditto for motion estimationarticulated object motion · PartNet-Mobility, 10 categoriesjoint axis angular error: 54.22 -> 0.069Improved
PARIS vs Ditto on whole-object reconstruction for objects with deep containersPARIS · Fridge, Washer, Oven, StorageCD-w: Fridge 2.68 vs Ditto 2.16; Washer 18.31 vs 7.29Hurt
PARIS on real-world scans vs Ditto for movable part geometryPARIS · MultiScan Fridge and StorageCD-m: Fridge 50.60 vs 67.54; Storage 20.35 vs 101.20Hurt
PARIS vs Ours-ICP (separate fields plus CSG and ICP) for static partPARIS · PartNet-MobilityCD-s: 4.50 vs 3.79No clear effect

Later papers that compared with this method

8 later accepted papers report PARIS as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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