# When Regression Meets Manifold Learning for Object Recognition and Pose Estimation

arXiv: https://arxiv.org/abs/1805.06400 · HTML: https://mlsanity.com/paper/1805.06400/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 8 of 8)

- [OSOP: A Multi-Stage One Shot Object Pose Estimation Framework](https://mlsanity.com/paper/2203.15533/) (2022)
- [OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation](https://mlsanity.com/paper/2203.01072/) (2022)
- [DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation](https://mlsanity.com/paper/2207.02805/) (2022)
- [DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimation](https://mlsanity.com/paper/2402.12647/) (2024)
- [Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Frames](https://mlsanity.com/paper/2503.03726/) (2025)
- [A Probabilistic Rotation Representation for Symmetric Shapes With an Efficiently Computable Bingham Loss Function](https://mlsanity.com/paper/2305.18947/) (2023)
- [Probabilistic Rotation Representation With an Efficiently Computable Bingham Loss Function and Its Application to Pose Estimation](https://mlsanity.com/paper/2203.04456/) (2022)
- [PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens](https://mlsanity.com/paper/2311.17504/) (2023)

## Abstract (arXiv)

In this work, we propose a method for object recognition and pose estimation from depth images using convolutional neural networks. Previous methods addressing this problem rely on manifold learning to learn low dimensional viewpoint descriptors and employ them in a nearest neighbor search on an estimated descriptor space. In comparison we create an efficient multi-task learning framework combining manifold descriptor learning and pose regression. By combining the strengths of manifold learning using triplet loss and pose regression, we could either estimate the pose directly reducing the complexity compared to NN search, or use learned descriptor for the NN descriptor matching. By in depth experimental evaluation of the novel loss function we observed that the view descriptors learned by the network are much more discriminative resulting in almost 30% increase regarding relative pose accuracy compared to related works. On the other hand, regarding directly regressed poses we obtained important improvement compared to simple pose regression. By leveraging the advantages of both manifold learning and regression tasks, we are able to improve the current state-of-the-art for object recognition and pose retrieval that we demonstrate through in depth experimental evaluation.