SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.17123 · CVPR · 2023

Masked and Adaptive Transformer for Exemplar Based Image Translation

Nannan Wang, Yuhao Lin, Fei Gao, Gang Xu, Biao Ma, Chang Jiang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 10 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.

RepositoryRoleRan
AiArt-HDU/MATEBIT — 10 of 11
FunctionStatusWhere it lives
AdaBlock Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("46185d38c66d915f")
CoordAtt Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("a364013be1afea2e")
LayerNorm Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("91d27ae48f10c634")
PositionalNorm2d Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("cabca479cad0531f")
SPADE Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("93da98f4f6845b01")
SignWithSigmoidGrad Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("70bbb1a234bbec73")
dynamic_attention Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("fd6117bfc579efa5")
feature_normalize Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("2ab25c1da9832507")
h_sigmoid Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("7e179a91bb50201f")
h_swish Ran AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("5e356c9d5f8f95df")
DynamicTransformerBlock Not yet run AiArt-HDU/MATEBIT/models/networks/dynast_transformer.py
code served (permissive licence) · get_code("77eb59f07e359be1")

Repositories linked to this paper

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

Abstract

We present a novel framework for exemplar based image translation. Recent advanced methods for this task mainly focus on establishing cross-domain semantic correspondence, which sequentially dominates image generation in the manner of local style control. Unfortunately, crossdomain semantic matching is challenging; and matching errors ultimately degrade the quality of generated images. To overcome this challenge, we improve the accuracy of matching on the one hand, and diminish the role of matching in image generation on the other hand. To achieve the former, we propose a masked and adaptive transformer (MAT) for learning accurate cross-domain correspondence, and executing context-aware feature augmentation. To achieve the latter, we use source features of the input and global style codes of the exemplar, as supplementary information, for decoding an image. Besides, we devise a novel contrastive style learning method, for acquire quality-discriminative style representations, which in turn benefit high-quality image generation. Experimental results show that our method, dubbed MATEBIT, performs considerably better than state-of-the-art methods, in diverse image translation tasks. The codes are available at https://github.com/AiArt-HDU/MATEBIT.

For agents

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

get_harvested_code_for_paper("2303.17123")
get_code_for_paper("2303.17123")
have("2303.17123")

Connect an agent — have() is free.