AI Paper Atlas

Research map / 3D vision / Face and shape

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Nick Heppert, Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu, Rares Andrei Ambrus, Jeannette Bohg, Abhinav Valada, Thomas Kollar

CVPR 2023 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 32 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 a single-shot stereo-image pipeline instead of the two-stage A-SDF pipelineCARTO · Full scene reconstruction, synthetic test setmAP IOU50: 10.4 -> 31.5Improved
use a single-shot stereo-image pipeline instead of the two-stage A-SDF pipelineCARTO · Full scene reconstruction, synthetic test setmAP IOU25: 33.9 -> 64.0Improved
use a single-shot stereo-image pipeline instead of the two-stage A-SDF pipelineCARTO · Full scene reconstruction, synthetic test set20°30cm pose accuracy: 70.8 -> 76.6Improved
use a single-shot stereo-image pipeline instead of the two-stage A-SDF pipelineCARTO · Full scene reconstruction, two-object inferenceTotal time: 64.262 -> 1.092Improved
add joint-space similarity regularization, including pre-training and post-epoch optimization (ablation)CARTO decoder · Canonical reconstruction task, seven-category meanChamfer distance (CD): 2.246 -> 1.192Improved
add joint-space similarity regularization, including pre-training and post-epoch optimization (ablation)CARTO decoder · Canonical reconstruction task, revolute categories meanJoint state error: 35.892° -> 11.512°Improved
add joint-space similarity regularization, including pre-training and post-epoch optimization (ablation)CARTO decoder · Canonical reconstruction task, seven-category meanJoint type accuracy: 0.646 -> 0.908Improved
train CARTO jointly across categories rather than only on one categoryCARTO decoder · Canonical reconstruction task, seven-category meanChamfer distance (CD): 1.190 -> 1.192No clear effect
train CARTO jointly across categories rather than only on one categoryCARTO decoder · Canonical reconstruction task, revolute categories meanJoint state error: 12.474° -> 11.512°Mixed
replace stereo RGB with RGB-D input (ablation)CARTO-D · Full scene reconstruction, synthetic test setmAP IOU50: 31.5 -> 38.2Improved
replace stereo RGB with RGB-D input (ablation)CARTO-D · Real-world test datasetmeaningful detectionsHurt
apply A-SDF test-time adaptation by jointly optimizing the shape code, joint state, and network weightsA-SDF · Canonical reconstruction taskChamfer distance: 13.339Mixed

Later papers that compared with this method

2 later accepted papers report CARTO as a baseline in their results tables; 2 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