# CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation

arXiv: https://arxiv.org/abs/1909.13476 · HTML: https://mlsanity.com/paper/1909.13476/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagery](https://mlsanity.com/paper/2101.09553/) (2021)
- [MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network](https://mlsanity.com/paper/2208.01172/) (2022)
- [SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation](https://mlsanity.com/paper/2208.08338/) (2022)
- [SyMFM6D: Symmetry-aware Multi-directional Fusion for Multi-View 6D Object Pose Estimation](https://mlsanity.com/paper/2307.00306/) (2023)
- [HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation](https://mlsanity.com/paper/2510.10177/) (2025)
- [Multistream ValidNet: Improving 6D Object Pose Estimation by Automatic Multistream Validation](https://mlsanity.com/paper/2106.06684/) (2021)
- [Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation](https://mlsanity.com/paper/2504.01298/) (2025)
- [MVTOP: Multi-View Transformer-based Object Pose-Estimation](https://mlsanity.com/paper/2508.03243/) (2025)
- [Robust PnP on a Neuromorphic Processor for Object Pose Estimation](https://mlsanity.com/paper/2607.16834/) (2026)

## Abstract (arXiv)

We present a new approach for a single view, image-based object pose estimation. Specifically, the problem of culling false positives among several pose proposal estimates is addressed in this paper. Our proposed approach targets the problem of inaccurate confidence values predicted by CNNs which is used by many current methods to choose a final object pose prediction. We present a network called CullNet, solving this task. CullNet takes pairs of pose masks rendered from a 3D model and cropped regions in the original image as input. This is then used to calibrate the confidence scores of the pose proposals. This new set of confidence scores is found to be significantly more reliable for accurate object pose estimation as shown by our results. Our experimental results on multiple challenging datasets (LINEMOD and Occlusion LINEMOD) reflects the utility of our proposed method. Our overall pose estimation pipeline outperforms state-of-the-art object pose estimation methods on these standard object pose estimation datasets. Our code is publicly available on https://github.com/kartikgupta-at-anu/CullNet.