SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1810.08771 · 2018

Image Inpainting via Generative Multi-column Convolutional Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 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
shepnerd/inpainting_gmcnn canonical 9 of 12
tlatkowski/inpainting-gmcnn-keras reimplementation 1 of 1
FunctionStatusWhere it lives
f2uint Ran shepnerd/inpainting_gmcnn/tensorflow/util/util.py
code served (permissive licence) · get_code("e6bbab52d3ddea75")
gauss_kernel Ran shepnerd/inpainting_gmcnn/tensorflow/net/ops.py
code served (permissive licence) · get_code("c5bc38ee9334ced5")
gauss_kernel Ran shepnerd/inpainting_gmcnn/pytorch/util/utils.py
code served (permissive licence) · get_code("23913d3031134cec")
generate_mask_rect Ran shepnerd/inpainting_gmcnn/tensorflow/util/util.py
code served (permissive licence) · get_code("b1331905adc5865e")
generate_rect_mask Ran shepnerd/inpainting_gmcnn/pytorch/util/utils.py
code served (permissive licence) · get_code("1ea87123e59cd723")
gradient_penalty Ran shepnerd/inpainting_gmcnn/pytorch/model/loss.py
code served (permissive licence) · get_code("685b99c187056ddf")
init_net Ran shepnerd/inpainting_gmcnn/pytorch/model/layer.py
code served (permissive licence) · get_code("8f8e91beb67bca00")
l2normalize Ran shepnerd/inpainting_gmcnn/pytorch/model/layer.py
code served (permissive licence) · get_code("bedff51745d2cf84")
postprocess_image Ran tlatkowski/inpainting-gmcnn-keras/predict.py
code served (permissive licence) · get_code("f94f52013566fd4f")
random_interpolate Ran shepnerd/inpainting_gmcnn/pytorch/model/loss.py
code served (permissive licence) · get_code("587edd4f057b0cb4")
free_form_mask_tf Not yet run shepnerd/inpainting_gmcnn/tensorflow/net/ops.py
code served (permissive licence) · get_code("1959726f4defa0e2")
np_free_form_mask Not yet run shepnerd/inpainting_gmcnn/pytorch/util/utils.py
code served (permissive licence) · get_code("e32ed92be303826d")
np_free_form_mask Not yet run shepnerd/inpainting_gmcnn/tensorflow/net/ops.py
code served (permissive licence) · get_code("0c044ee49bfaec49")

Repositories linked to this paper

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

Abstract

In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF regularization is adopted to enhance local details. The multi-column network combined with the reconstruction and MRF loss propagates local and global information derived from context to the target inpainting regions. Extensive experiments on challenging street view, face, natural objects and scenes manifest that our method produces visual compelling results even without previously common post-processing.

For agents

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

get_harvested_code_for_paper("1810.08771")
get_code_for_paper("1810.08771")
have("1810.08771")

Connect an agent — have() is free.