SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1703.06868 · 2017

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Serge Belongie, Xun Huang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 41 functions out of this paper's own repositories and ran 28 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

FunctionStatusWhere it lives
AdaIN Ran CellEight/Pytorch-Adaptive-Instance-Normalization/AdaIN.py
pointer only (licence: NONE) · get_code("1b5a7b593632abec")
AdaIN Ran aadhithya/AdaIN-pytorch/model.py
pointer only (licence: GPL-3.0) · get_code("b6bda511442174ee")
AdaIN Ran tyui592/adain_pytorch/network.py
pointer only (licence: NONE) · get_code("1e75525dca622a5b")
AdaptiveInstanceNorm Ran ptran1203/style_transfer/model.py
pointer only (licence: NONE) · get_code("80f6c4540623a906")
MixStyle Ran KaiyangZhou/mixstyle-release/reid/models/mixstyle.py
code served (permissive licence) · get_code("7b69aa89b55f1907")
Net Ran Jwrede/neural_style_transfer/network.py
pointer only (licence: NONE) · get_code("feb8354419bc47a3")
Net Ran gs18113/AdaIN-TensorFlow2/model.py
pointer only (licence: NONE) · get_code("e9c0b7f386130131")
Norm Ran dongkwani/upcsc/trainers/adain/adain.py
code served (permissive licence) · get_code("70413403e7bd4032")
UndoNorm Ran dongkwani/upcsc/trainers/adain/adain.py
code served (permissive licence) · get_code("20d93f7c8062709d")
_check_shapes Ran J3698/AdaIN-reimplementation/adain.py
pointer only (licence: NONE) · get_code("6b522b9ea394b717")
_match_normalized_to_stats Ran J3698/AdaIN-reimplementation/adain.py
pointer only (licence: NONE) · get_code("a1f744f78d31de67")
adaIN Ran ZVK/talking_heads/network/blocks.py
pointer only (licence: GPL-3.0) · get_code("5eec2a5c6c95f4ab")
adaIN Ran Jwrede/neural_style_transfer/network.py
pointer only (licence: NONE) · get_code("a44a1f4fc02b2471")
ada_in_func Ran abhishtagatya/paintgan/algorithm/ada_in_comp/model.py
pointer only (licence: NONE) · get_code("f47797a80e241835")
adain Ran J3698/AdaIN-reimplementation/adain.py
pointer only (licence: NONE) · get_code("336fa3afbebc8219")
adain Ran yjunej/AdaIN-tf2/model.py
pointer only (licence: NONE) · get_code("ced95aa1ec3ddcb2")
adain Ran gs18113/AdaIN-TensorFlow2/model.py
pointer only (licence: NONE) · get_code("96ad7bbb7f8171f7")
adaptive_instance_norm Ran cryu854/ArbitraryStyle-tfjs/model.py
pointer only (licence: NONE) · get_code("277eca3b84592e36")
adaptive_instance_normalization Ran bethgelab/stylize-datasets/function.py
pointer only (licence: NOASSERTION) · get_code("bd9607443cdfbbe8")
adaptive_instance_normalization Ran dongkwani/upcsc/trainers/adain/adain.py
code served (permissive licence) · get_code("16679a24b9881031")
calc_feature_stats Ran J3698/AdaIN-reimplementation/adain.py
pointer only (licence: NONE) · get_code("33f304ede0c2b810")
calc_mean_std Ran bethgelab/stylize-datasets/function.py
pointer only (licence: NOASSERTION) · get_code("abe85479c8ccd9a7")
compute_mean_std Ran aadhithya/AdaIN-pytorch/model.py
pointer only (licence: GPL-3.0) · get_code("5c064a93e7042c2c")
deprocessing Ran JeongsolKim/BiS400_term_project/StyleTransfer.py
pointer only (licence: NONE) · get_code("4ef3b0e9747d6981")
expand_moments_dim Ran gs18113/AdaIN-TensorFlow2/model.py
pointer only (licence: NONE) · get_code("457244674e377df9")
get_mean_std Ran abhishtagatya/paintgan/algorithm/ada_in_comp/model.py
pointer only (licence: NONE) · get_code("fc194f2d050dbd6d")
preprocessing Ran JeongsolKim/BiS400_term_project/StyleTransfer.py
pointer only (licence: NONE) · get_code("994ad288a2dff0d9")
std_and_mean Ran Jwrede/neural_style_transfer/network.py
pointer only (licence: NONE) · get_code("2bb3accb9ec4b9df")
AdaIN Not yet run dongkwani/upcsc/trainers/adain/adain.py
code served (permissive licence) · get_code("0dd85d8525c0fba8")
AdaptiveInstanceNorm Not yet run abhishtagatya/paintgan/algorithm/ada_in_comp/model.py
pointer only (licence: NONE) · get_code("dff326cf89112719")
AdaptiveInstanceNormalization Not yet run srihari-humbarwadi/adain-tensorflow2.x/adain/model/layers/adaptive_instance_normalization.py
code served (permissive licence) · get_code("6c204664e722b241")
adain Not yet run eridgd/WCT-TF/ops.py
code served (permissive licence) · get_code("6acb2016293c036e")
assert_shape Not yet run J3698/AdaIN-reimplementation/adain.py
pointer only (licence: NONE) · get_code("9debb36434e3f2cf")
decoder Not yet run JeongsolKim/BiS400_term_project/StyleTransfer.py
pointer only (licence: NONE) · get_code("246cb3106fe953a1")
defineHeatmapNetwork Not yet run asindel/artfacepoints/network.py
code served (permissive licence) · get_code("ec43c13d4a962175")
defineLRscheduler Not yet run asindel/artfacepoints/network.py
code served (permissive licence) · get_code("b9af50ae977def20")
encoder Not yet run JeongsolKim/BiS400_term_project/StyleTransfer.py
pointer only (licence: NONE) · get_code("8c0e5a509dab7362")
getRelPaths Not yet run asindel/artfacepoints/data_utils.py
code served (permissive licence) · get_code("c868992c0f0ff321")
is_image_file Not yet run asindel/artfacepoints/data_utils.py
code served (permissive licence) · get_code("eafb5322ecc71e47")
styletransfer Not yet run JeongsolKim/BiS400_term_project/StyleTransfer.py
pointer only (licence: NONE) · get_code("8091756b8c40713c")
tensor2imRGB Not yet run asindel/artfacepoints/data_utils.py
code served (permissive licence) · get_code("f3c73b49545c08c8")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1703.06868")
get_code_for_paper("1703.06868")
have("1703.06868")

Connect an agent — have() is free.