# Neural Object Learning for 6D Pose Estimation Using a Few Cluttered Images

arXiv: https://arxiv.org/abs/2005.03717 · HTML: https://mlsanity.com/paper/2005.03717/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

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

- [Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions](https://mlsanity.com/paper/2203.17234/) (2022)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting](https://mlsanity.com/paper/2104.02527/) (2021)
- [TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2212.12902/) (2022)
- [StablePose: Learning 6D Object Poses from Geometrically Stable Patches](https://mlsanity.com/paper/2102.09334/) (2021)
- [PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking](https://mlsanity.com/paper/2209.07589/) (2022)
- [DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency](https://mlsanity.com/paper/2104.03658/) (2021)
- [DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation](https://mlsanity.com/paper/2112.08775/) (2021)
- [Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2306.00129/) (2023)
- [Depth from Camera Motion and Object Detection](https://mlsanity.com/paper/2103.01468/) (2021)
- [Learning Better Keypoints for Multi-Object 6DoF Pose Estimation](https://mlsanity.com/paper/2308.07827/) (2023)
- [Weakly Supervised Learning of Keypoints for 6D Object Pose Estimation](https://mlsanity.com/paper/2203.03498/) (2022)
- [SABER-6D: Shape Representation Based Implicit Object Pose Estimation](https://mlsanity.com/paper/2408.05867/) (2024)
- [Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstruction](https://mlsanity.com/paper/2501.14896/) (2025)

## Abstract (arXiv)

Recent methods for 6D pose estimation of objects assume either textured 3D models or real images that cover the entire range of target poses. However, it is difficult to obtain textured 3D models and annotate the poses of objects in real scenarios. This paper proposes a method, Neural Object Learning (NOL), that creates synthetic images of objects in arbitrary poses by combining only a few observations from cluttered images. A novel refinement step is proposed to align inaccurate poses of objects in source images, which results in better quality images. Evaluations performed on two public datasets show that the rendered images created by NOL lead to state-of-the-art performance in comparison to methods that use 13 times the number of real images. Evaluations on our new dataset show multiple objects can be trained and recognized simultaneously using a sequence of a fixed scene.