SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.02735 · 2018

Deep Back-Projection Networks For Super-Resolution

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 9 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
LEEPEIQIN/EDSR pwc_unofficial 5 of 5
alterzero/DBPN-Pytorch pwc_unofficial 4 of 8
akashpalrecha/superres-deformable pwc_unofficial 0 of 1
FunctionStatusWhere it lives
calc_psnr Ran LEEPEIQIN/EDSR/src/utility.py
code served (permissive licence) · get_code("d4592ac83c04a5fd")
default_conv Ran LEEPEIQIN/EDSR/src/model/common.py
code served (permissive licence) · get_code("8b0e794d4d8f9b13")
is_image_file Ran alterzero/DBPN-Pytorch/dataset.py
code served (permissive licence) · get_code("0516d5020cce56da")
load_img Ran alterzero/DBPN-Pytorch/dataset.py
code served (permissive licence) · get_code("27ebc73345cd00a0")
make_optimizer Ran LEEPEIQIN/EDSR/src/utility.py
code served (permissive licence) · get_code("5eed111fb0fb051b")
projection_conv Ran LEEPEIQIN/EDSR/src/model/ddbpn.py
code served (permissive licence) · get_code("3cadb1fed3be1893")
quantize Ran LEEPEIQIN/EDSR/src/utility.py
code served (permissive licence) · get_code("b1c1acd3c89a39f3")
rescale_img Ran alterzero/DBPN-Pytorch/dataset.py
code served (permissive licence) · get_code("25678766a66c3ac4")
str2bool Ran alterzero/DBPN-Pytorch/eval_gan.py
code served (permissive licence) · get_code("25c7475539e39da4")
denorm Not yet run alterzero/DBPN-Pytorch/utils.py
code served (permissive licence) · get_code("754eaaec87e45177")
gated_conv Not yet run akashpalrecha/superres-deformable/src/model/cgc_edsr.py
code served (permissive licence) · get_code("b70e2f411ef9239a")
gram_matrix Not yet run alterzero/DBPN-Pytorch/utils.py
code served (permissive licence) · get_code("4be7bb2418de3fb9")
norm Not yet run alterzero/DBPN-Pytorch/utils.py
code served (permissive licence) · get_code("5178867afe8613af")
x8_forward Not yet run alterzero/DBPN-Pytorch/eval_gan.py
code served (permissive licence) · get_code("007d490d5ea4d153")

Repositories linked to this paper

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

Abstract

The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components. We show that extending this idea to allow concatenation of features across up- and down-sampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8x across multiple data sets.

For agents

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

get_harvested_code_for_paper("1803.02735")
get_code_for_paper("1803.02735")
have("1803.02735")

Connect an agent — have() is free.