SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.07835 · 2018

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 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
YadiraF/PRNet canonical 8 of 10
FunctionStatusWhere it lives
P2sRt Ran YadiraF/PRNet/utils/estimate_pose.py
code served (permissive licence) · get_code("07326d46bad4e31e")
get_point_weight Ran YadiraF/PRNet/utils/render.py
code served (permissive licence) · get_code("50572306e7c01f27")
isPointInTri Ran YadiraF/PRNet/utils/render.py
code served (permissive licence) · get_code("05f23476146a0cfe")
isRotationMatrix Ran YadiraF/PRNet/utils/estimate_pose.py
code served (permissive licence) · get_code("5d64cc8f381e2dbd")
matrix2angle Ran YadiraF/PRNet/utils/estimate_pose.py
code served (permissive licence) · get_code("b3226b96c3df432a")
plot_kpt Ran YadiraF/PRNet/utils/cv_plot.py
code served (permissive licence) · get_code("eb07d94367663cae")
plot_vertices Ran YadiraF/PRNet/utils/cv_plot.py
code served (permissive licence) · get_code("273ff544685cb7f1")
render_texture Ran YadiraF/PRNet/utils/render.py
code served (permissive licence) · get_code("51145c8552370f7c")
frontalize Not yet run YadiraF/PRNet/utils/rotate_vertices.py
code served (permissive licence) · get_code("2c47072c128b71f5")
plot_pose_box Not yet run YadiraF/PRNet/utils/cv_plot.py
code served (permissive licence) · get_code("e90ac38cb687dd7d")

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 propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin.

For agents

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

get_harvested_code_for_paper("1803.07835")
get_code_for_paper("1803.07835")
have("1803.07835")

Connect an agent — have() is free.