AI Paper Atlas

Research map / Image generation / GANs

Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

Chuan Li, Michael Wand

ECCV 2016 · Image generation › GANs · approach: Large-scale GAN latent analysis · 1,529 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 adversarial (Markovian GAN) loss instead of pixel-level Euclidean loss for training the decoder (ablation)MGANs decoder · Picasso style transfer, training and test photosvisual quality (qualitative)Improved
compare at neural encoding level instead of pixel level (ablation)VAE decoder · Picasso style transfervisual quality (qualitative)Improved
use pre-trained VGG_19 features for the discriminator instead of training it from pixels (ablation)MDANs discriminator · unguided texture synthesisvisual quality (qualitative)Improved
feed discriminator from lower layer relu2_1 (patch 16) instead of relu3_1 (ablation)MDANs discriminator · unguided texture synthesissharpness vs structure (qualitative)Mixed
feed discriminator from higher layer relu4_1 (patch 4) instead of relu3_1 (ablation)MDANs discriminator · unguided texture synthesisstructure vs flexibility (qualitative)Mixed
use larger patches (16) instead of 8 in discriminator (ablation)MDANs discriminator · unguided texture synthesisrigidity (qualitative)Mixed
add convolutional layer to the discriminator (ablation)MDANs discriminator · texture synthesissynthesis quality (qualitative)Improved
add further layers to the discriminator beyond one convolutional layer (ablation)MDANs discriminator · texture synthesissynthesis quality (qualitative)No clear effect
increase discriminator channels from 4 to 64 (ablation)MDANs discriminator · texture synthesissynthesis quality (qualitative)Improved
increase discriminator channels from 64 to 128 (ablation)MDANs discriminator · texture synthesissynthesis quality (qualitative)No clear effect
make the generator more complex (more layers or channels) (ablation)MGANs generator · texture synthesissynthesis quality (qualitative)No clear effect
initialize discriminator with a network pre-trained on 50 face images (ablation)MDANs · style transfer to face imagesiterations needed (qualitative): 500 iterations without -> 50 iterations withImproved

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