# VLM6D: VLM based 6Dof Pose Estimation based on RGB-D Images

arXiv: https://arxiv.org/abs/2511.00120 · HTML: https://mlsanity.com/paper/2511.00120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 10 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator](https://mlsanity.com/paper/2102.12145/) (2021)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2203.09418/) (2022)
- [6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark](https://mlsanity.com/paper/2203.05701/) (2022)
- [Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting](https://mlsanity.com/paper/2104.02527/) (2021)
- [Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation](https://mlsanity.com/paper/2203.14531/) (2022)
- [RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Images](https://mlsanity.com/paper/2405.08483/) (2024)

## Abstract (arXiv)

The primary challenge in computer vision is precisely calculating the pose of 6D objects, however many current approaches are still fragile and have trouble generalizing from synthetic data to real-world situations with fluctuating lighting, textureless objects, and significant occlusions. To address these limitations, VLM6D, a novel dual-stream architecture that leverages the distinct strengths of visual and geometric data from RGB-D input for robust and precise pose estimation. Our framework uniquely integrates two specialized encoders: a powerful, self-supervised Vision Transformer (DINOv2) processes the RGB modality, harnessing its rich, pre-trained understanding of visual grammar to achieve remarkable resilience against texture and lighting variations. Concurrently, a PointNet++ encoder processes the 3D point cloud derived from depth data, enabling robust geometric reasoning that excels even with the sparse, fragmented data typical of severe occlusion. These complementary feature streams are effectively fused to inform a multi task prediction head. We demonstrate through comprehensive experiments that VLM6D obtained new SOTA performance on the challenging Occluded-LineMOD, validating its superior robustness and accuracy.