AI Paper Atlas

Research map / Image generation / Editing and style transfer

Neural Collage Transfer: Artistic Reconstruction via Material Manipulation

Ganghun Lee, Minji Kim, Yunsu Lee, Minsu Lee, Byoung-Tak Zhang

ICCV 2023 · Image generation › Editing and style transfer · approach: Texture and sketch synthesis · 4 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 model-based SAC instead of model-free SAC (ablation)collage agent · Scene target, DTD materials, 64x64MSE: 0.042 -> 0.031Improved
use SAC instead of DDPG in model-based agent (ablation)collage agent · Scene target, DTD materials, 64x64MSE: 0.039 -> 0.031Improved
use SAC instead of DDPG in model-free agent (ablation)collage agent · Scene target, DTD materials, 64x64MSE: 0.305 -> 0.042Improved
use a learned WGAN-GP discriminator reward instead of MSE reward (ablation)collage agent · Scene target, DTD materials, 64x64MSE: 0.122 -> 0.031Improved
use WGAN-GP instead of SNGAN discriminator for reward (ablation)collage agent · Scene target, DTD materials, 64x64MSE: 0.040 -> 0.031Improved
use WGAN-GP instead of GNGAN discriminator for reward (ablation)collage agent · Scene target, DTD materials, 64x64MSE: 0.084 -> 0.031Improved
increase the multi-scale collage scale from 32 to 128 (ablation)multi-scale collage · CLIP score contentCLIP score content: 0.280 -> 0.225Hurt
increase the multi-scale collage scale from 32 to 128 (ablation)multi-scale collage · CLIP score collageCLIP vote collage: 0.100 -> 1.000Improved
increase the number of scraps from 10 to 30 (ablation)collage agent · Scene target, DTD materialsMSEMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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