AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Paint Transformer: Feed Forward Neural Painting With Stroke Prediction

Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Ruifeng Deng, Xin Li, Errui Ding, Hao Wang

ICCV 2021 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 110 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
add pixel loss (ablation)Paint Transformer · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)pixel loss: 0.081 -> 0.056Improved
add pixel loss (ablation)Paint Transformer · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)perceptual loss: 1.012 -> 0.807Improved
add parameter L1 loss (ablation)Paint Transformer · Synthesized random strokesstroke parameter L1 distance D_L1: 0.267 -> 0.083Improved
add parameter L1 loss (ablation)Paint Transformer · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)pixel loss: 0.074 -> 0.056Improved
add Wasserstein loss (ablation)Paint Transformer · Synthesized random strokesWasserstein distance D_W: 0.034 -> 0.018Improved
add Wasserstein loss (ablation)Paint Transformer · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)pixel loss: 0.069 -> 0.056Improved
add confidence (BCE) loss (ablation)Paint Transformer · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)pixel loss: 0.071 -> 0.056Improved
add confidence (BCE) loss (ablation)Paint Transformer · Synthesized random strokespixel loss: 0.052 -> 0.042Improved
use Paint Transformer instead of Optimneural painting · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)pixel loss: 0.059 -> 0.056Improved
use Paint Transformer instead of RLneural painting · Real images (100 landscapes, 100 WikiArt, 100 FFHQ)pixel loss: 0.040 -> 0.056Hurt
use Paint Transformer instead of Optim for stroke predictionneural painting · Synthesized random strokesstroke parameter L1 distance D_L1: 0.137 -> 0.083Improved
use Paint Transformer instead of Optimneural painting · Inference time, 512x512 imageinference time (s): 521.447 -> 0.304Improved

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