AI Paper Atlas

Research map / 3D vision / 3D generation

Monte Carlo Scene Search for 3D Scene Understanding

Shreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar, Chetan S. Kumar, Friedrich Fraundorfer, Vincent Lepetit

CVPR 2021 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 28 citations (OpenAlex)

Check 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 the local node score instead of the simulation's global score to update Q (ablation)MCSS · 12 challenging scenes, layout recoveryglobal score: 9%Improved
use the local node score instead of the simulation's global score to update Q (ablation)MCSS · 12 challenging scenes, object recoveryglobal score: 15%Improved
use MCSS instead of random tree searchlayout recovery · 12 challenging scenesglobal score: 15%Improved
use MCSS instead of random tree searchobject recovery · 12 challenging scenesglobal score: 42%Improved
include the estimated layout when evaluating object hypotheses (ablation)MCSS object retrieval · 12 challenging scenes, chairprecision: 0.58 -> 0.65Improved
include the estimated layout when evaluating object hypotheses (ablation)MCSS object retrieval · 12 challenging scenes, chairrecall: 0.61 -> 0.84Improved
include the estimated layout when evaluating object hypotheses (ablation)MCSS object retrieval · 12 challenging scenes, tableprecision: 0.48 -> 0.66Improved
include the estimated layout when evaluating object hypotheses (ablation)MCSS object retrieval · 12 challenging scenes, tablerecall: 0.34 -> 0.58Improved
use MCSS rather than VoteNet detection with one retrieved model per boxobject retrieval · Scan2CAD, chairaccuracy: 42.02 -> 74.32Improved
use MCSS rather than VoteNet detection with one retrieved model per boxobject retrieval · Scan2CAD, sofaaccuracy: 27.70 -> 78.70Improved
use MCSS rather than VoteNet detection with one retrieved model per boxobject retrieval · Scan2CAD, tableaccuracy: 18.52 -> 24.28Hurt

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