# Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images

arXiv: https://arxiv.org/abs/2211.07491 · HTML: https://mlsanity.com/paper/2211.07491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 64 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](https://mlsanity.com/paper/1911.11130/) (2019)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [FS6D: Few-Shot 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2203.14628/) (2022)
- [Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning](https://mlsanity.com/paper/1807.03146/) (2018)
- [3D Human Pose Estimation from a Single Image via Distance Matrix Regression](https://mlsanity.com/paper/1611.09010/) (2016)
- [C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion](https://mlsanity.com/paper/1909.02533/) (2019)
- [Viewpoints and Keypoints](https://mlsanity.com/paper/1411.6067/) (2014)
- [Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/1511.09439/) (2015)
- [Deep Non-Rigid Structure from Motion](https://mlsanity.com/paper/1908.00052/) (2019)
- [Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation](https://mlsanity.com/paper/1908.00999/) (2019)
- [Improving Semantic Segmentation via Self-Training](https://mlsanity.com/paper/2004.14960/) (2020)
- [Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion](https://mlsanity.com/paper/1904.11960/) (2019)
- [To The Point: Correspondence-driven monocular 3D category reconstruction](https://mlsanity.com/paper/2106.05662/) (2021)

## Abstract (arXiv)

We study the problem of estimating 3D shape and pose of an object in terms of keypoints, from a single 2D image. The shape and pose are learned directly from images collected by categories and their partial 2D keypoint annotations.. In this work, we first propose an end-to-end training framework for intermediate 2D keypoints extraction and final 3D shape and pose estimation. The proposed framework is then trained using only the weak supervision of the intermediate 2D keypoints. Additionally, we devise a semi-supervised training framework that benefits from both labeled and unlabeled data. To leverage the unlabeled data, we introduce and exploit the piece-wise planar hull prior of the canonical object shape. These planar hulls are defined manually once per object category, with the help of the keypoints. On the one hand, the proposed method learns to segment these planar hulls from the labeled data. On the other hand, it simultaneously enforces the consistency between predicted keypoints and the segmented hulls on the unlabeled data. The enforced consistency allows us to efficiently use the unlabeled data for the task at hand. The proposed method achieves comparable results with fully supervised state-of-the-art methods by using only half of the annotations. Our source code will be made publicly available.