SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.09117 · 2019

SelFlow: Self-Supervised Learning of Optical Flow

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 7 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
ppliuboy/SelFlow canonical 7 of 12
FunctionStatusWhere it lives
config_dict Ran ppliuboy/SelFlow/config/extract_config.py
code served (permissive licence) · get_code("3dd5c269c8110162")
flow_horizontal_flip Ran ppliuboy/SelFlow/data_augmentation.py
code served (permissive licence) · get_code("177a030ea67ee72e")
flow_vertical_flip Ran ppliuboy/SelFlow/data_augmentation.py
code served (permissive licence) · get_code("a8dc427be3802afc")
lrelu Ran ppliuboy/SelFlow/utils.py
code served (permissive licence) · get_code("69e0961ea54f416c")
read_pfm Ran ppliuboy/SelFlow/flowlib.py
code served (permissive licence) · get_code("f8c75b69f9e7a932")
rgb_bgr Ran ppliuboy/SelFlow/utils.py
code served (permissive licence) · get_code("7a1e9253c132b589")
tf_warp Ran ppliuboy/SelFlow/warp.py
code served (permissive licence) · get_code("34af5f8b54be1bf2")
flow_to_color Not yet run ppliuboy/SelFlow/flowlib.py
code served (permissive licence) · get_code("3208c90e2942acfa")
get_pixel_value Not yet run ppliuboy/SelFlow/warp.py
code served (permissive licence) · get_code("76d9ba255fb4180c")
mvn Not yet run ppliuboy/SelFlow/utils.py
code served (permissive licence) · get_code("167f43828fef8e2f")
random_crop Not yet run ppliuboy/SelFlow/data_augmentation.py
code served (permissive licence) · get_code("2265da3e272fe1dd")
read_flo Not yet run ppliuboy/SelFlow/flowlib.py
code served (permissive licence) · get_code("63f11096bd0174c0")

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 self-supervised learning approach for optical flow. Our method distills reliable flow estimations from non-occluded pixels, and uses these predictions as ground truth to learn optical flow for hallucinated occlusions. We further design a simple CNN to utilize temporal information from multiple frames for better flow estimation. These two principles lead to an approach that yields the best performance for unsupervised optical flow learning on the challenging benchmarks including MPI Sintel, KITTI 2012 and 2015. More notably, our self-supervised pre-trained model provides an excellent initialization for supervised fine-tuning. Our fine-tuned models achieve state-of-the-art results on all three datasets. At the time of writing, we achieve EPE=4.26 on the Sintel benchmark, outperforming all submitted methods.

For agents

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

get_harvested_code_for_paper("1904.09117")
get_code_for_paper("1904.09117")
have("1904.09117")

Connect an agent — have() is free.