AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DiffCollage: Parallel Generation of Large Content With Diffusion Models

Qinsheng Zhang, Jiaming Song, Xun Huang, Yongxin Chen, Ming-Yu Liu

CVPR 2023 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 61 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 DiffCollage instead of autoregressive reconstructionDiffusion generation on the internal landscape dataset · Internal landscape datasetFID+: 8.97 -> 4.54Improved
Use DiffCollage instead of autoregressive replacementDiffusion generation on the internal landscape dataset · Internal landscape datasetTime: 14.99 -> 6.47Improved
Use DiffCollage instead of reconstructionImage generation on LHQ 256² · LHQ 256²FID+: 18.37 -> 16.43Improved
Use DiffCollage instead of reconstructionImage generation on Tower 256² · Tower 256²FID+: 19.56 -> 13.27Improved
Use DiffCollage instead of reconstructionMDM long-duration motion generation · HumanML3D test set, 24-second motionR Precision (top 3): 0.585 -> 0.611Improved
Use DiffCollage instead of reconstructionMDM long-duration motion generation · HumanML3D test set, 24-second motionFID: 1.012 -> 0.605Improved
Use DiffCollage instead of reconstructionMDM long-duration motion generation · HumanML3D test set, 24-second motionMultimodal Dist: 5.716 -> 5.569Improved
Use DiffCollage instead of replacementMDM long-duration motion generation · HumanML3D test set, 24-second motionDiversity: 9.184 -> 9.372Improved

Later papers that compared with this method

2 later accepted papers report DiffCollage as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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