AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Learning Deep Sketch Abstraction

Umar Riaz Muhammad, Yongxin Yang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales

CVPR 2018 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 0 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 ranked reward instead of basic reward (ablation)Sketch abstraction model · QuickDraw test, human sketches, abstraction levels 1–3accuracy: 87.60% -> 88.20%; 78.80% -> 80.80%; 68.00% -> 70.40%Improved
use ranked reward instead of basic reward (ablation)Sketch abstraction model · QuickDraw test, synthesized sketches, abstraction levels 1–3accuracy: 92.60% -> 94.20%; 88.40% -> 90.80%; 73.20% -> 79.40%Improved
learn stroke-segment removal rather than remove segments randomly (ablation)Sketch abstraction model · QuickDraw test, human sketches, abstraction levels 1–3accuracy: 85.00% -> 88.20%; 74.60% -> 80.80%; 64.20% -> 70.40%Improved
learn stroke-segment removal rather than remove segments randomly (ablation)Sketch abstraction model · QuickDraw test, synthesized sketches, abstraction levels 1–3accuracy: 89.96% -> 94.20%; 80.20% -> 90.80%; 69.20% -> 79.40%Improved
train FG-SBIR with sketches synthesized by the abstraction pipeline instead of simplified edge-maps (ablation)FG-SBIR model · Shoe-V2Top1 matching accuracy: 16.67% -> 21.17%Improved
train FG-SBIR with sketches synthesized by the abstraction pipeline instead of simplified edge-maps (ablation)FG-SBIR model · Chair-V2Top1 matching accuracy: 34.67% -> 41.80%Improved
train FG-SBIR with sketches synthesized by the abstraction pipeline instead of the cited synthesis model (ablation)FG-SBIR model · Shoe-V2Top1 matching accuracy: 8.86% -> 21.17%Improved
train FG-SBIR with sketches synthesized by the abstraction pipeline instead of the cited synthesis model (ablation)FG-SBIR model · Chair-V2Top1 matching accuracy: 31.27% -> 41.80%Improved
include multiple abstraction levels during FG-SBIR training and testingFG-SBIR model · Shoe-V2 and Chair-V2Top1 matching accuracyImproved
replace the softmax temperature adjustment with a probability-distribution shift to control abstractionSketch abstraction model · Sketch abstractionabstraction-level controlImproved
generate photo-to-sketch outputs by edge-map preprocessing and abstraction rather than encoder-decoder image translationPhoto-to-sketch synthesis · QMUL Shoe-V2visual appealImproved
use the learned abstraction model rather than random stroke removalSketch abstraction model · Human studyaesthetic preference: 64.3 ± 4.59Improved

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