AI Paper Atlas

Research map / 3D vision / 3D generation

Map2World: Segment Map Conditioned Text to 3D World Generation

Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang, Jiaolong Yang, Kyoung Mu Lee

ECCV 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 1 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 concatenation-MLP conditioning instead of IP-Adapter (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)FID (DINOv2): 80.81 -> 32.67Improved
use concatenation-MLP conditioning instead of IP-Adapter (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)PSNR: 20.28 -> 22.53Improved
use concatenation-MLP conditioning instead of IP-Adapter (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)LPIPS: 0.2499 -> 0.2137Improved
avoid classifier-free guidance in fine-tuning and sampling (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)FID (CLIP): 21.32 -> 11.79Improved
avoid classifier-free guidance in fine-tuning and sampling (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)PSNR: 21.95 -> 22.53Improved
add SLAT decoder fine-tuning on small scene cubes (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)FID (CLIP): 13.17 -> 11.79Improved
add SLAT decoder fine-tuning on small scene cubes (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)PSNR: 22.08 -> 22.53Improved
add SLAT decoder fine-tuning on small scene cubes (ablation)detail enhancer · Detail enhancer ablation (1,500 test cubes)FID (Inception v3): 17.89 -> 16.98Improved
add spectral (3D FFT) parameterization of sparse structure for initial noise optimization (ablation)scale-aware initial latent optimization · Scale optimization with learning rate 9.0IoU and Dice: approximately 0.9 on average within five optimization stepsImproved
lower learning rate to 1.0 without spectral parameterization (ablation)initial latent optimization · Scale optimizationconvergence speed: avoids divergence but requires significantly more optimization stepsMixed
replace SynCity with Map2Worldworld generator · World generation (35 NuiScene43 captions)GPTscore average: 7.48 -> 7.93Improved
replace SynCity with Map2Worldworld generator · World generation (35 NuiScene43 captions)World Quality (WQ): 7.25 -> 7.76Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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