# Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency

arXiv: https://arxiv.org/abs/1712.05765 · HTML: https://mlsanity.com/paper/1712.05765/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2017.

## Built on by (most cited first, 14 of 14)

- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection](https://mlsanity.com/paper/2203.14956/) (2022)
- [Task-specific Inconsistency Alignment for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15345/) (2022)
- [Regressive Domain Adaptation for Unsupervised Keypoint Detection](https://mlsanity.com/paper/2103.06175/) (2021)
- [SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation](https://mlsanity.com/paper/2304.03251/) (2023)
- [Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles](https://mlsanity.com/paper/2103.14098/) (2021)
- [Domain Adaptive Hand Keypoint and Pixel Localization in the Wild](https://mlsanity.com/paper/2203.08344/) (2022)
- [Deep Image Harmonization by Bridging the Reality Gap](https://mlsanity.com/paper/2103.17104/) (2021)
- [Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.17877/) (2024)
- [RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications](https://mlsanity.com/paper/2404.03962/) (2024)
- [MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds](https://mlsanity.com/paper/2304.01554/) (2023)
- [3D Keypoint Estimation Using Implicit Representation Learning](https://mlsanity.com/paper/2306.11529/) (2023)

## Abstract (arXiv)

In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or similar objects should be consistent with each other. Such view consistency can provide effective regularization for keypoint prediction on unlabeled instances. In addition, we introduce a geometric alignment term to regularize predictions in the target domain. The resulting loss function can be effectively optimized via alternating minimization. We demonstrate the effectiveness of our approach on real datasets and present experimental results showing that our approach is superior to state-of-the-art general-purpose domain adaptation techniques.