AI Paper Atlas

Research map / 3D vision / 3D generation

Repurposing 3D Generative Model for Autoregressive Layout Generation

Haoran Feng, Yifan Niu, Zehuan Huang, Yang-Tian Sun, Chunchao Guo, Yuxin Peng, Lu Sheng

CVPR 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 4 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 identity-aware embedding (ablation)base 3D generative model · LayoutVLM layout benchmarkPSA: 16.7 -> 71.4Improved
add identity-aware embedding (ablation)base 3D generative model · LayoutVLM layout benchmarkcollision-free (CF): 75.6 -> 89.1Improved
add holistic-guidance distillation (ablation)base + id-aware embedding · LayoutVLM layout benchmarkgeneration time (s): 144.1 -> 24.5Improved
add holistic-guidance distillation (ablation)base + id-aware embedding · LayoutVLM layout benchmarkPSA: 71.4 -> 59.7Hurt
add step-wise guidance (ablation)base + id-aware + holistic guidance · LayoutVLM layout benchmarkPSA: 59.7 -> 78.8Improved
add step-wise guidance (ablation)base + id-aware + holistic guidance · LayoutVLM layout benchmarkcollision-free (CF): 79.5 -> 97.3Improved
add step-wise guidance (ablation)base + id-aware + holistic guidance · LayoutVLM layout benchmarkrotation coherency: 58.7 -> 77.1Improved
use LaviGen instead of LayoutVLMLayoutVLM · LayoutVLM layout benchmarkPSA: 58.8 -> 78.8Improved
use LaviGen instead of LayoutVLMLayoutVLM · LayoutVLM layout benchmarkgeneration time (s): 75.5 -> 24.3Improved
use LaviGen instead of LayoutGPTLayoutGPT · LayoutVLM layout benchmarkpositional coherency: 80.8 -> 76.9Hurt
use LaviGen instead of LayoutVLMLayoutVLM · User studyoverall quality preference: 36.5 -> 55.6Improved

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