# Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation

arXiv: https://arxiv.org/abs/2504.15134 · HTML: https://mlsanity.com/paper/2504.15134/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [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)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2007.08454/) (2020)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting](https://mlsanity.com/paper/2203.07918/) (2022)
- [SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation](https://mlsanity.com/paper/2108.08367/) (2021)
- [Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks](https://mlsanity.com/paper/2207.05444/) (2022)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection](https://mlsanity.com/paper/2406.10700/) (2024)
- [Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model](https://mlsanity.com/paper/2404.14966/) (2024)
- [HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios](https://mlsanity.com/paper/2212.10428/) (2022)
- [SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation](https://mlsanity.com/paper/2311.11125/) (2023)
- [HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation](https://mlsanity.com/paper/2303.15743/) (2023)
- [Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation](https://mlsanity.com/paper/2403.19527/) (2024)
- [IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation](https://mlsanity.com/paper/2303.13479/) (2023)
- [VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations](https://mlsanity.com/paper/2308.09916/) (2023)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Robust 6D Object Pose Estimation by Learning RGB-D Features](https://mlsanity.com/paper/2003.00188/) (2020)
- [GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation](https://mlsanity.com/paper/2502.04293/) (2025)
- [PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation](https://mlsanity.com/paper/2108.09916/) (2021)

## Built on by (most cited first, 1 of 1)

- [Thinking with Cameras: Active Visual Reasoning via Dynamic Viewpoint Control for Surveillance Video Understanding](https://mlsanity.com/paper/2609.06475/) (2026)

## Abstract (arXiv)

Category-level object pose estimation aims to predict the 6D pose and size of previously unseen instances from predefined categories, requiring strong generalization across diverse object instances. Although many previous methods attempt to mitigate intra-class variations, they often struggle with instances exhibiting complex geometries or significant deviations from canonical shapes. To address this issue, we propose INKL-Pose, a novel category-level object pose estimation framework that enables INstance-adaptive Keypoint Learning with local-to-global geometric aggregation. Specifically, our method first predicts semantically consistent and geometrically informative keypoints using an Instance-Adaptive Keypoint Detector, then refines them: (1) a Local Keypoint Feature Aggregator capturing fine-grained geometries, and (2) a Global Keypoint Feature Aggregator using bidirectional Mamba for structural consistency. To enable bidirectional modeling in Mamba, we introduce a simple yet effective Feature Sequence Flipping strategy that preserves spatial coherence while constructing backward feature sequence. Additionally, we design a surface loss and a separation loss to encourage uniform coverage and spatial diversity in keypoint distribution. The resulting keypoints are mapped to a canonical space for 6D pose and size regression. Extensive experiments on CAMERA25, REAL275, and HouseCat6D show that INKL-Pose achieves state-of-the-art performance with 16.7M parameters and runs at 36 FPS on an NVIDIA RTX 4090D GPU.