AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

LaLaLoc++: Global Floor Plan Comprehension for Layout Localisation in Unvisited Environments

Henry Howard-Jenkins, Victor Adrian Prisacariu

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Inverse rendering with neural fields · 17 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
replace LaLaLoc with LaLaLoc++ (dense floor plan comprehension + transformer)floor plan localisation · Structured3Dmedian error (cm): 8.3 -> 5.2Improved
replace LaLaLoc with LaLaLoc++floor plan localisation · Structured3Daccuracy <1m: 87.5% -> 92.3%Improved
replace LaLaLoc with LaLaLoc++floor plan localisation · Zillow Indoor Datasetmedian error (cm): 13.1 -> 9.3Improved
replace rendering-based LaLaLoc with direct 2D plan inferenceLaLaLoc · Structured3D inference timetotal inference time (s): 4.65 -> 0.13Improved
train Phi_plan to mimic LaLaLoc layout branch (ablation)LaLaLoc++ Phi_plan · Structured3Dmedian error (cm): 8.3 -> 8.4No clear effect
train Phi_plan with layout decoding loss instead of mimicking (ablation)LaLaLoc++ Phi_plan · Structured3Dmedian error (cm): 8.4 -> 5.7Improved
add transformer encoder to the image embedding branch (ablation)LaLaLoc++ Phi_image · Structured3Dmedian error (cm): 5.7 -> 5.2Improved
use full-size latent floor plan instead of 8x subsampling (ablation)LaLaLoc++ refinement · Structured3Dmedian error (cm): 6.5 -> 5.2Improved
use full-size latent floor plan instead of 4x subsampling (ablation)LaLaLoc++ refinement · Structured3Dmedian error (cm): 5.3 -> 5.2No clear effect
use 5 down/up-sample layers in Phi_plan instead of 3 (ablation)LaLaLoc++ Phi_plan · Structured3Dmedian error (cm): 12.9 -> 5.2Improved
use 5 layers instead of 4 in Phi_plan (ablation)LaLaLoc++ Phi_plan · Structured3Dmedian error (cm): 6.0 -> 5.2Improved
use 6 layers instead of 5 in Phi_plan (ablation)LaLaLoc++ Phi_plan · Structured3Dmedian error (cm): 5.2 -> 5.3No clear effect

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