# Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation

arXiv: https://arxiv.org/abs/2603.27533 · HTML: https://mlsanity.com/paper/2603.27533/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [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)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again](https://mlsanity.com/paper/1711.10006/) (2017)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2007.08454/) (2020)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2001.09322/) (2020)
- [FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism](https://mlsanity.com/paper/2103.07054/) (2021)
- [DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency](https://mlsanity.com/paper/2103.06526/) (2021)
- [GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting](https://mlsanity.com/paper/2203.07918/) (2022)
- [Single-Stage 6D Object Pose Estimation](https://mlsanity.com/paper/1911.08324/) (2019)
- [SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation](https://mlsanity.com/paper/2108.08367/) (2021)
- [Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks](https://mlsanity.com/paper/2108.08755/) (2021)
- [Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image](https://mlsanity.com/paper/2109.06161/) (2021)
- [DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimation](https://mlsanity.com/paper/2402.12647/) (2024)
- [ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation](https://mlsanity.com/paper/2111.10524/) (2021)
- [FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects](https://mlsanity.com/paper/2310.12974/) (2023)
- [GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondence](https://mlsanity.com/paper/2311.13777/) (2023)

## Abstract (arXiv)

Object pose estimation is a fundamental task in 3D vision with applications in robotics, AR/VR, and scene understanding. We address the challenge of category-level 9-DoF pose estimation (6D pose + 3Dsize) from RGB-D input, without relying on CAD models during inference. Existing depth-only methods achieve strong results but ignore semantic cues from RGB, while many RGB-D fusion models underperform due to suboptimal cross-modal fusion that fails to align semantic RGB cues with 3D geometric representations. We propose DeMo-Pose, a hybrid architecture that fuses monocular semantic features with depth-based graph convolutional representations via a novel multimodal fusion strategy. To further improve geometric reasoning, we introduce a novel Mesh-Point Loss (MPL) that leverages mesh structure during training without adding inference overhead. Our approach achieves real-time inference and significantly improves over state-of-the-art methods across object categories, outperforming the strong GPV-Pose baseline by 3.2% on 3D IoU and 11.1% on pose accuracy on the REAL275 benchmark. The results highlight the effectiveness of depth-RGB fusion and geometry-aware learning, enabling robust category-level 3D pose estimation for real-world applications.