AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models

Junyi Zhang, Jiaqi Guo, Shizhao Sun, Jian-Guang Lou, Dongmei Zhang

ICCV 2023 · Image generation › Fast diffusion sampling · approach: Discrete diffusion solvers · 56 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 block-wise transition matrix with piece-wise linear schedule instead of generic D3PM absorbing/uniform (ablation)LayoutDiffusion · RICO Un-GenFID: 4.985 -> 2.490Improved
add discretized Gaussian transition for coordinate tokens instead of uniform (ablation)LayoutDiffusion · RICO Un-GenFID: 3.174 -> 2.490Improved
add absorbing transition for type tokens instead of uniform (ablation)LayoutDiffusion · RICO Un-GenmIoU: 0.593 -> 0.620Improved
use piece-wise linear type schedule (type noise only late) instead of linear (ablation)LayoutDiffusion · RICO Un-GenmIoU: 0.580 -> 0.620Improved
use beta_t=g/(T-t+eps)^h coordinate schedule instead of linear (ablation)LayoutDiffusion · RICO Un-GenAlign.: 0.202 -> 0.069Improved
reduce diffusion steps from 1000+ to 200 (ablation)LayoutDiffusion · RICO Un-GenFID: 2.295 -> 2.490No clear effect
reduce diffusion steps to 100 (ablation)LayoutDiffusion · RICO Un-GenFID: 2.490 -> 3.875Hurt
replace LayoutFormer++ with LayoutDiffusion without retraining for refinementRefinement · RICOFID: 3.666 -> 0.549Improved
replace LayoutFormer++ with LayoutDiffusion for unconditional generationUn-Gen · PubLayNetFID: 47.082 -> 8.625Improved
use LayoutDiffusion in place of Diffusion-LMUn-Gen · RICO / PubLayNetmIoU: 0.662 -> 0.620 (RICO)Mixed

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