AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning To Warp for Style Transfer

Xiao-Chang Liu, Yong-Liang Yang, Peter Hall

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 34 citations (OpenAlex)

Check 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 the learned feed-forward non-parametric warp instead of per-instance optimizationGeometric style transfer · RTX 2080 Ti, geometric warpingruntime (s): 83–133 -> 0.3–1.2Improved
Add geometric warping before texture rendering (ablation)NST style transfer · Human subjective similaritystyle similarity preference: 60% to 70%Improved
Use a multi-scale texture-rendering pyramid rather than a single pyramid layer (ablation)Texture rendering module · Style transfer image qualityrendering qualityImproved
Iteratively refine the warp field over multiple forward passes (ablation)Warp network · Geometric style transferwarp accuracyImproved

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