# MONET: Multiview Semi-supervised Keypoint Detection via Epipolar Divergence

arXiv: https://arxiv.org/abs/1806.00104 · HTML: https://mlsanity.com/paper/1806.00104/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2018.

## Built on by (most cited first, 4 of 4)

- [Supervision by Registration and Triangulation for Landmark Detection](https://mlsanity.com/paper/2101.09866/) (2021)
- [OutCast: Outdoor Single-image Relighting with Cast Shadows](https://mlsanity.com/paper/2204.09341/) (2022)
- [Proactive Multi-Camera Collaboration For 3D Human Pose Estimation](https://mlsanity.com/paper/2303.03767/) (2023)
- [GeoBlur: Epipolar Geometry Estimation from a Single Motion-Blurred Image](https://mlsanity.com/paper/2605.01552/) (2026)

## Abstract (arXiv)

This paper presents MONET -- an end-to-end semi-supervised learning framework for a keypoint detector using multiview image streams. In particular, we consider general subjects such as non-human species where attaining a large scale annotated dataset is challenging. While multiview geometry can be used to self-supervise the unlabeled data, integrating the geometry into learning a keypoint detector is challenging due to representation mismatch. We address this mismatch by formulating a new differentiable representation of the epipolar constraint called epipolar divergence---a generalized distance from the epipolar lines to the corresponding keypoint distribution. Epipolar divergence characterizes when two view keypoint distributions produce zero reprojection error. We design a twin network that minimizes the epipolar divergence through stereo rectification that can significantly alleviate computational complexity and sampling aliasing in training. We demonstrate that our framework can localize customized keypoints of diverse species, e.g., humans, dogs, and monkeys.