SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04154 · CVPR · 2021

Unsupervised Human Pose Estimation through Transforming Shape Templates

Athanasios Vlontzos, Bernhard Kainz, Simon Ellershaw, Luca Schmidtke, Anna Lukens, Tomoki Arichi

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 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
lschmidtke/shape_templates canonical 7 of 9
FunctionStatusWhere it lives
compute_anchor_loss Ran lschmidtke/shape_templates/src/core/utils/losses.py
code served (permissive licence) · get_code("3e915aa903575ba6")
compute_boundary_loss Ran lschmidtke/shape_templates/src/core/utils/losses.py
code served (permissive licence) · get_code("3fa27226f242b41d")
draw_shape Ran lschmidtke/shape_templates/src/core/utils/helper.py
code served (permissive licence) · get_code("174942967930e188")
get_3rd_point Ran lschmidtke/shape_templates/src/core/utils/transforms.py
code served (permissive licence) · get_code("9084d28f30c5495b")
get_bbx Ran lschmidtke/shape_templates/processing/h36m_processing.py
code served (permissive licence) · get_code("beb11c9b064fb863")
get_dir Ran lschmidtke/shape_templates/src/core/utils/transforms.py
code served (permissive licence) · get_code("5d546e1ecbee1866")
id_generator Ran lschmidtke/shape_templates/processing/h36m_processing.py
code served (permissive licence) · get_code("a389d0fb57120bdf")
load_config Not yet run lschmidtke/shape_templates/src/core/utils/helper.py
code served (permissive licence) · get_code("a5ac42bbf3a2026c")
transform_anchor_points Not yet run lschmidtke/shape_templates/src/core/utils/transforms.py
code served (permissive licence) · get_code("89dda06edbba1976")

Repositories linked to this paper

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

Abstract

Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking. In the medical context, the latter may be an important biomarker for neurological impairments in infants. Whilst many methods exist, their application has been limited by the need for well annotated large datasets and the inability to generalize to humans of different shapes and body compositions, e.g. children and infants. In this paper we present a novel method for learning pose estimators for human adults and infants in an unsupervised fashion. We approach this as a learnable template matching problem facilitated by deep feature extractors. Human-interpretable landmarks are estimated by transforming a template consisting of predefined body parts that are characterized by 2D Gaussian distributions. Enforcing a connectivity prior guides our model to meaningful human shape representations. We demonstrate the effectiveness of our approach on two different datasets including adults and infants. Project

For agents

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

get_harvested_code_for_paper("2105.04154")
get_code_for_paper("2105.04154")
have("2105.04154")

Connect an agent — have() is free.