3PoinTr: From Human Videos to Robot Policies with 3D Point-Track Plans

arXiv:2603.08485 · cs.RO · Submitted 2026-03-09 · Read on arXiv

cs.RO

Submitted: 2026-03-09

Updated: 2026-09-19

Project page: https://adamhung60.github.io/3PoinTr

Terminology

• Transformer — 9× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Distribution Shift — 5× in this paper · explained in 6 episodes
• Diffusion Policy — 4× in this paper
• Point Clouds — 4× in this paper · explained in 2 episodes
• Affordance — 3× in this paper · explained in 1 episode
• Sample Efficiency — 3× in this paper · explained in 4 episodes
• Average Displacement Error — 2× in this paper
• World Model — 2× in this paper · explained in 7 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Adaptive Selection — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Diffusion Policy (DP) — 1× in this paper · explained in 2 episodes
• Digital Twin — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• U-net architecture — 1× in this paper · explained in 3 episodes

Sources

• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
• Perceiver IO: A General Architecture for Structured Inputs & Outputs
• Any-point Trajectory Modeling for Policy Learning
• Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning
• AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation
• Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
• PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
• NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos
• Flow as the Cross-Domain Manipulation Interface
• 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
• FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects
• CoTracker: It is Better to Track Together
• 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
• Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
• RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
• R3M: A Universal Visual Representation for Robot Manipulation
• XIRL: Cross-embodiment Inverse Reinforcement Learning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving