# GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation

arXiv: https://arxiv.org/abs/2510.16777 · HTML: https://mlsanity.com/paper/2510.16777/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 19 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2311.11700/) (2023)
- [SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again](https://mlsanity.com/paper/1711.10006/) (2017)
- [BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth](https://mlsanity.com/paper/1703.10896/) (2017)
- [OnePose: One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2205.12257/) (2022)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [Self-supervised 6D Object Pose Estimation for Robot Manipulation](https://mlsanity.com/paper/1909.10159/) (2019)
- [NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2203.04802/) (2022)
- [6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model](https://mlsanity.com/paper/2407.15484/) (2024)
- [ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/2305.17934/) (2023)
- [Rigidity-Aware Detection for 6D Object Pose Estimation](https://mlsanity.com/paper/2303.12396/) (2023)
- [SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation](https://mlsanity.com/paper/2311.08190/) (2023)
- [NeRF-Feat: 6D Object Pose Estimation using Feature Rendering](https://mlsanity.com/paper/2406.13796/) (2024)
- [Object Gaussian for Monocular 6D Pose Estimation from Sparse Views](https://mlsanity.com/paper/2409.02581/) (2024)
- [PCKRF: Point Cloud Completion and Keypoint Refinement With Fusion Data for 6D Pose Estimation](https://mlsanity.com/paper/2210.03437/) (2022)
- [Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation](https://mlsanity.com/paper/2501.08038/) (2025)

## Abstract (arXiv)

Accurate 6D pose estimation of 3D objects is a fundamental task in computer vision, and current research typically predicts the 6D pose by establishing correspondences between 2D image features and 3D model features. However, these methods often face difficulties with textureless objects and varying illumination conditions. To overcome these limitations, we propose GS2POSE, a novel approach for 6D object pose estimation. GS2POSE formulates a pose regression algorithm inspired by the principles of Bundle Adjustment (BA). By leveraging Lie algebra, we extend the capabilities of 3DGS to develop a pose-differentiable rendering pipeline, which iteratively optimizes the pose by comparing the input image to the rendered image. Additionally, GS2POSE updates color parameters within the 3DGS model, enhancing its adaptability to changes in illumination. Compared to previous models, GS2POSE demonstrates accuracy improvements of 1.4%, 2.8% and 2.5% on the T-LESS, LineMod-Occlusion and LineMod datasets, respectively.