AI Paper Atlas

Research map / 3D vision / 3D generation

Robust Shape Fitting for 3D Scene Abstraction

Florian Kluger, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn

TPAMI 2024 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 6 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 occlusion-aware inlier counting at inference (ablation)cuboid fitting · NYU validation, depth inputOA-L2 AUC@20cm (%): 6.2 -> 56.3Improved
add occlusion-aware inlier counting at inference (ablation)cuboid fitting · NYU validationmean OA distance covered points (cm): 135.1 -> 6.4 (roughly 1.3 m -> 6.4 cm)Improved
add occlusion-aware inlier counting during training (sampling and loss) (ablation)cuboid fitting · NYU validationAUC: 0.2 to 1.0 percentage pointsImproved
add occlusion-aware inlier counting to Sequential RANSACSequential RANSAC · NYU depth inputmean OA distance covered points (cm): 139.3 -> 16.5Improved
use minimal set size C=6 instead of C=9 (ablation)cuboid fitting · NYU validationcoverage and AUC at fixed hypothesesImproved
use minimal set size C=6 instead of C=9 (ablation)cuboid fitting · NYU validationmean OA distance covered pointsNo clear effect
use neural solver instead of numerical solvercuboid fitting · NYU depth inputcomputation time (s): 7.63 -> 0.87Improved
use neural solver instead of numerical solvercuboid fitting · NYU depth inputAUC@20cm (%): 60.1 -> 49.4Hurt
use neural solver instead of numerical solvercuboid fitting · NYU depth inputnumber of primitives: 6.8 -> 3.9Improved
add EM refinement (ablation)numerical cuboid solver · NYU depth inputAUC@5cm (%): 29.9 -> 35.1Improved
add EM refinement (ablation)numerical cuboid solver · NYU depth inputcomputation time (s): 7.63 -> 9.02Hurt
add regularisation losses during end-to-end fine-tuning (ablation)full pipeline · NYUperformanceHurt

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