atlas

Research map / Image generation / Autoregressive and latent generation

Fast Texture Synthesis via Pseudo Optimizer

CVPR 2020 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 9 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 PO (ProPO) instead of MultiTexturefast texture synthesis · Floraltexture loss: 719.8 -> 645.9Helped
Use PO (ProPO) instead of WCTfast texture synthesis · Floraltexture loss: 2042.5 -> 645.9Helped
Use PO (ProPO) instead of Gatys et al.texture synthesis · Floraltexture loss: 90.1 -> 645.9Hurt
Use PO (ProPO) instead of MultiTexturefast texture synthesis · DTDtexture loss: 6639.0 -> 4672.5Helped
Use PO (ProPO) instead of WCTfast texture synthesis · DTDtexture loss: 6673.2 -> 4672.5Helped
Use PO (ProPO) instead of MultiTexturefast texture synthesis · Floraldiversity loss: 385.9 -> 397.1Helped
Use PO (ProPO) instead of WCTfast texture synthesis · Floraldiversity loss: 309.3 -> 397.1Helped
Use PO (ProPO) instead of Gatys et al.texture synthesis · Floraldiversity loss: 433.2 -> 397.1Hurt
Add progressive multi-stage refinement rather than using a single-stage AdaPO model (ablation)PO texture synthesis · Floraltexture lossHelped
Add progressive multi-stage refinement rather than using a single-stage AdaPO model (ablation)PO texture synthesis · FloraldiversityHelped

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