AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Dolfin: Diffusion Layout Transformers without Autoencoder

Yilin Wang, Zeyuan Chen, Liangjun Zhong, Zheng Ding, Zhuowen Tu

ECCV 2024 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 22 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
operate directly on input space instead of adding an MLP autoencoder latent space (ablation)Dolfin · PublayNet unconditionalFID: 15.50 -> 9.12Improved
operate directly on input space instead of MLP autoencoder (ablation)Dolfin · PublayNet unconditionalAlignment: 0.129 -> 0.074Improved
increase transformer size from 4x512 to 8x512 (ablation)Dolfin · PublayNet unconditionalFID: 9.12 -> 9.45No clear effect
reduce hidden size from 512 to 384 (ablation)Dolfin · PublayNet unconditionalFID: 9.12 -> 9.49No clear effect
use autoregressive diffusion (Dolfin-AR) instead of non-autoregressiveDolfin · PublayNet unconditionalAlignment: 0.074 -> 0.042Improved
use autoregressive diffusion (Dolfin-AR) instead of non-autoregressiveDolfin · PublayNet unconditionalFID: 9.12 -> 16.88Hurt
use Dolfin-AR on RICO unconditionalDolfin · RICO unconditionalMaxIoU: 0.42 -> 0.17Hurt
apply Dolfin to heavily overlapping RICO layoutsDolfin · RICO unconditionalFID: 13.00 (PLay) vs 15.38Hurt
Dolfin versus LT and LayoutGAN++ on line segment generationline segments · ShanghaiTech WireframeFID: 317.4 -> 92.1Improved

Earlier methods this paper compares with

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