mlsanityData to 14 Oct 2026

End to End Face Reconstruction via Differentiable PnP

arXiv 2409.14249 ↗First posted 21 Sep 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This is a challenge report of the ECCV 2022 WCPA Challenge, Face Reconstruction Track. Inside this report is a brief explanation of how we accomplish this challenge. We design a two-branch network to accomplish this task, whose roles are Face Reconstruction and Face Landmark Detection. The former outputs canonical 3D face coordinates. The latter outputs pixel coordinates, i.e. 2D mapping of 3D coordinates with head pose and perspective projection. In addition, we utilize a differentiable PnP (Perspective-n-Points) layer to finetune the outputs of the two branch. Our method achieves very competitive quantitative results on the MVP-Human dataset and wins a 3rd prize in the challenge.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 14 references that are in the map. First posted on arXiv 21 Sep 2024.

Builds on

10 of 14 references.

References · 10

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  5. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  6. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  7. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  8. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  9. 20226D Rotation Representation For Unconstrained Head Pose Estimationcited by 64
  10. 2021Riggable 3D Face Reconstruction via In-Network Optimizationcited by 31

Built on by

Not cited yet.