AI Paper Atlas

Research map / 3D vision / 3D generation

InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis With Semantic Graph Prior

Chenguo Lin, Yu-Chen Lin, Panwang Pan, Xuanyang Zhang, Yadong Mu

TPAMI 2025 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 7 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 independent-mask discrete diffusion graph prior instead of Gaussian diffusion (ablation)InstructLayout · 3D BedroomiRecall (%): 34.18 -> 73.64Improved
add independent masking instead of joint masking of nodes and attributes (ablation)InstructLayout · 3D BedroomiRecall (%): 34.21 -> 73.64Improved
add mask states instead of uniform transition matrices (ablation)InstructLayout · 3D BedroomFID: 139.61 -> 114.78Improved
use random-shuffled non-invariant graph modeling instead of permutation-invariant (ablation)InstructLayout · 3D BedroomiRecall (%): 70.49 -> 73.64Improved
use permutation non-invariant graph modeling (ablation)InstructLayout · 3D BedroomFID: 116.53 -> 114.78Improved
reduce graph-prior timesteps from 100 to 50 (ablation)InstructLayout · 2D posteriRecall (%): 78.268 -> 78.833No clear effect
reduce graph-prior timesteps from 100 to 25 (ablation)InstructLayout · 2D posteriRecall (%): 78.268 -> 77.862No clear effect
reduce LayoutDM timesteps from 110 to 35 (ablation)LayoutDM · 2D posteriRecall (%): 65.841 -> 61.825Hurt
use two-stage graph prior + layout decoder instead of ATISSATISS · 3D BedroomiRecall (%): 48.13 -> 73.64Improved
use two-stage graph prior + layout decoder instead of DiffuSceneDiffuScene · 3D Living roomFID: 122.20 -> 110.39Improved
use two-stage discrete+continuous diffusion instead of single-stage LayoutDMLayoutDM · 2D posteriRecall (%): 62.999 -> 78.451Improved
use two-stage diffusion instead of continuous DDPMDDPM · 2D posterOve x100: 17.573 -> 0.785Improved

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