# Object Gaussian for Monocular 6D Pose Estimation from Sparse Views

arXiv: https://arxiv.org/abs/2409.02581 · HTML: https://mlsanity.com/paper/2409.02581/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 58 references that are in the map.
- First posted on arXiv 4 Sep 2024.

## Builds on (most cited first, 5 of 5)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [SparseGS: Sparse View Synthesis using 3D Gaussian Splatting](https://mlsanity.com/paper/2312.00206/) (2023)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting](https://mlsanity.com/paper/2403.10683/) (2024)

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

- [BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation](https://mlsanity.com/paper/2504.07955/) (2025)
- [GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos](https://mlsanity.com/paper/2412.02267/) (2024)
- [GS2POSE: Marry Gaussian Splatting to 6D Object Pose Estimation](https://mlsanity.com/paper/2510.16777/) (2025)
- [GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Tracking](https://mlsanity.com/paper/2609.39116/) (2026)

## Abstract (arXiv)

Monocular object pose estimation, as a pivotal task in computer vision and robotics, heavily depends on accurate 2D-3D correspondences, which often demand costly CAD models that may not be readily available. Object 3D reconstruction methods offer an alternative, among which recent advancements in 3D Gaussian Splatting (3DGS) afford a compelling potential. Yet its performance still suffers and tends to overfit with fewer input views. Embracing this challenge, we introduce SGPose, a novel framework for sparse view object pose estimation using Gaussian-based methods. Given as few as ten views, SGPose generates a geometric-aware representation by starting with a random cuboid initialization, eschewing reliance on Structure-from-Motion (SfM) pipeline-derived geometry as required by traditional 3DGS methods. SGPose removes the dependence on CAD models by regressing dense 2D-3D correspondences between images and the reconstructed model from sparse input and random initialization, while the geometric-consistent depth supervision and online synthetic view warping are key to the success. Experiments on typical benchmarks, especially on the Occlusion LM-O dataset, demonstrate that SGPose outperforms existing methods even under sparse view constraints, under-scoring its potential in real-world applications.