AI Paper Atlas

Research map / 3D vision / 3D generation

Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models

Nicky Kriplani, Yiwen Zhang, Angelina Wang, Hadar Averbuch-Elor

NeurIPS 2026 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces ArchWorld, a geographically diverse benchmark of 3D architectural landmarks, and uses it to analyze errors of current 3D foundation models in single feed-forward scene reconstruction.

Problem

Internet-scale photo collections of landmarks are highly challenging for 3D foundation models that estimate scene structure in a single feed-forward pass, and their failure modes on geographically diverse architecture are not well characterized.

Approach

A benchmark of 3D architectural landmarks with high geographic coverage and rich metadata, used for a thorough error analysis of current 3DFMs.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply ArchAttend (gradient-ascent step on token representations toward anchor architectural element)DA3 · ArchWorld, all scenesmedian normalized Chamfer distance: 10.36 -> 8.92Improved
apply ArchAttendDA3 · ArchWorld North Americamedian normalized Chamfer distance: 18.83 -> 12.82Improved
apply ArchAttendDA3 · ArchWorld Tower architecturemedian normalized Chamfer distance: 21.04 -> 16.29Improved
apply ArchAttendDA3 · ArchWorld regional disparitydisparity (max minus min regional median): 11.26 -> 6.96Improved
apply ArchAttendDA3 · ArchWorld architecture disparitydisparity (max minus min type median): 13.75 -> 9.14Improved
use a single scene-agnostic step size eta instead of best of five (ablation)ArchAttend on DA3 · ArchWorldregional gap closed (%): closes about 41.7% of the regional gapImproved
train on more data from a region (data representation)3DFMs (VGGT, DA3, pi3) · ArchWorld regional performanceregional error vs training representationNo clear effect
normalize Chamfer distance by scene bounding box size (ablation)3DFM evaluation · ArchWorld regional disparitiescorrelation with data representationMixed
use stronger overall 3DFM (pi3)3DFMs · ArchWorld regionsgeographic disparity: pi3 East Asia 2.75 vs Southeast Asia 1.34No clear effect
add construction year as predictor of error3DFMs · ArchWorld (149 annotated scenes)reconstruction errorNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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.

Experimental setup

Benchmarks: ArchWorld

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