A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

Neuroscience Inspired Agent Reasoning Framework

[ICRA'25] Code for "MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model".

[CVPR 2025] Any6D: Model-free 6D Pose Estimation of Novel Objects

Project Page for Paper "Neural Brain: A Neuroscience-inspired Framework for Embodied Agents".

Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation

[ECCV 2024] GenPose++: A generative category-level 6D object pose estimation and tracking approach proposed in Omni6DPose.

[ECCV 2024] Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

Code for "Novel Object 6D Pose Estimation with a Single Reference View".

[TPAMI 2025] Code for "Diff9D: Diffusion-Based Domain-Generalized Category-Level 9DoF Object Pose Estimation".

RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery

[CVPR 2024 Highlight] PyTorch implementation of "Object Pose Estimation via the Aggregation of Diffusion Features"

FS6D: Few-Shot 6D Pose Estimation of Novel Objects, CVPR 2022

[TPAMI 2024] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Welcome to the project repository for POPE (Promptable Pose Estimation), a state-of-the-art technique for 6-DoF pose estimation of any object in any scene using a single reference.

[CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Robust Outlier Rejection for 3D Registration with Variational Bayes (Accepted by CVPR-2023)

[ECCV 2024] SRPose: Two-view Relative Pose Estimation with Sparse Keypoints

Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

PyTorch implementation of "DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses" (CVPR 2024)

[CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".

6D Pose Estimation in the Wild

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022