SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.05481 · 2020

STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 11 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
pgodet/star_flow canonical 11 of 13
FunctionStatusWhere it lives
apply_transform_to_params Ran pgodet/star_flow/augmentations.py
code served (permissive licence) · get_code("fc31c500a57e244d")
compute_color Ran pgodet/star_flow/utils/flow.py
code served (permissive licence) · get_code("dc5b20ec12d3ae87")
conv Ran pgodet/star_flow/models/irr_modules.py
code served (permissive licence) · get_code("9db5fbaedd8ed8b4")
denormalize_coords Ran pgodet/star_flow/augmentations.py
code served (permissive licence) · get_code("49af4e3fbd112a56")
f1_score_bal_loss Ran pgodet/star_flow/losses.py
code served (permissive licence) · get_code("e90ca7d9eaedb594")
flow_to_png Ran pgodet/star_flow/utils/flow.py
code served (permissive licence) · get_code("c39cf1b0372a9391")
flow_to_png_middlebury Ran pgodet/star_flow/utils/flow.py
code served (permissive licence) · get_code("3b3ea1e0c955f8fe")
get_default_logging_format Ran pgodet/star_flow/logger.py
code served (permissive licence) · get_code("6eaba3d6df46f7ed")
normalize_coords Ran pgodet/star_flow/augmentations.py
code served (permissive licence) · get_code("c92c8a169968453b")
subtract_mean Ran pgodet/star_flow/models/irr_modules.py
code served (permissive licence) · get_code("538f9abf58b6c890")
upsample_factor2 Ran pgodet/star_flow/models/irr_modules.py
code served (permissive licence) · get_code("606dfd0419b77fe8")
f1_score Not yet run pgodet/star_flow/losses.py
code served (permissive licence) · get_code("e351a73a9141e59d")
fbeta_score Not yet run pgodet/star_flow/losses.py
code served (permissive licence) · get_code("0185c542a4ae3ac4")

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 new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell. It includes (i) a temporal recurrence based on conveying learned features rather than optical flow estimates; (ii) an occlusion detection process which is coupled with optical flow estimation and therefore uses a very limited number of extra parameters. The resulting STaRFlow algorithm gives state-of-the-art performances on MPI Sintel and Kitti2015 and involves significantly less parameters than all other methods with comparable results.

For agents

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

get_harvested_code_for_paper("2007.05481")
get_code_for_paper("2007.05481")
have("2007.05481")

Connect an agent — have() is free.