Skip to content

seathiefwang/RankPose

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
src
 
 
 
 
 
 

RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation

Paper

RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation

Abstract

We address the challenging problem of RGB image-based head pose estimation. We first reformulate head pose representation learning to constrain it to a bounded space. Head pose represented as vector projection or vector angles shows helpful to improving. performance. Further, a ranking loss combined with MSE regression loss is proposed. The ranking loss supervises a neural network with paired samples of the same person and penalises incorrect ordering of pose prediction. Analysis on this new loss function suggests it contributes to a better local feature extractor, where features are generalised to Abstract Landmarks which are pose-related features instead of pose-irrelevant information such as identity, age, and lighting. Extensive experiments show that our method significantly outperforms the current state-of-the-art schemes on public datasets:
AFLW2000 and BIWI. Our model achieves significant improvements over previous SOTA MAE on AFLW2000 and BIWI from 4.50 [11] to 3.66 and from 4.0 [24] to 3.71 respectively.

Dependencies

  • pytorch >= 0.4.1
  • albumentations
  • opencv2
  • yaml
pip3 install requirements.txt

Datasets

Train data

Face Alignment Across Large Poses: A 3D Solution

300W-LP

Test data

AFLW2000 BIWI Kinect

Train and test

Training

CUDA_VISIBLE_DEVICES=0 python3 train.py ../config/headpose_resnet.yaml

Testing

CUDA_VISIBLE_DEVICES=0 python3 test.py

Pretrained model

Will be available for download in the future.

About

RankPose: Learning Generalised Feature with Rank Supervision for Head Pose Estimation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages