# ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations

arXiv: https://arxiv.org/abs/2509.11125 · HTML: https://mlsanity.com/paper/2509.11125/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 34 of its 51 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 34)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [RVT: Robotic View Transformer for 3D Object Manipulation](https://mlsanity.com/paper/2306.14896/) (2023)
- [RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins](https://mlsanity.com/paper/2504.13059/) (2025)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation](https://mlsanity.com/paper/2211.09423/) (2022)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning](https://mlsanity.com/paper/2409.03403/) (2024)
- [Visual Reinforcement Learning with Self-Supervised 3D Representations](https://mlsanity.com/paper/2210.07241/) (2022)
- [Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning](https://mlsanity.com/paper/2402.02500/) (2024)
- [Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning](https://mlsanity.com/paper/2407.15815/) (2024)
- [View-Invariant Policy Learning via Zero-Shot Novel View Synthesis](https://mlsanity.com/paper/2409.03685/) (2024)
- [G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation](https://mlsanity.com/paper/2411.18369/) (2024)
- [A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning](https://mlsanity.com/paper/2210.04561/) (2022)
- [RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation](https://mlsanity.com/paper/2406.18977/) (2024)
- [MoVie: Visual Model-Based Policy Adaptation for View Generalization](https://mlsanity.com/paper/2307.00972/) (2023)
- [Point Cloud Models Improve Visual Robustness in Robotic Learners](https://mlsanity.com/paper/2404.18926/) (2024)
- [Towards a Unified Framework of Contrastive Learning for Disentangled Representations](https://mlsanity.com/paper/2311.04774/) (2023)
- [Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments](https://mlsanity.com/paper/2504.19139/) (2025)
- [DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments](https://mlsanity.com/paper/2507.21981/) (2025)
- [Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras](https://mlsanity.com/paper/2404.14064/) (2024)
- [Spatial Transformer for 3D Point Clouds](https://mlsanity.com/paper/1906.10887/) (2019)
- [Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models](https://mlsanity.com/paper/2410.23820/) (2024)

## Built on by (most cited first, 5 of 5)

- [PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation](https://mlsanity.com/paper/2601.17885/) (2026)
- [From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model](https://mlsanity.com/paper/2607.05396/) (2026)
- [Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics](https://mlsanity.com/paper/2602.21203/) (2026)
- [DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration](https://mlsanity.com/paper/2603.07545/) (2026)
- [The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection](https://mlsanity.com/paper/2607.02322/) (2026)

## Abstract (arXiv)

Deploying visual reinforcement learning (RL) policies in real-world manipulation is often hindered by camera viewpoint changes. A policy trained from a fixed front-facing camera may fail when the camera is shifted -- an unavoidable situation in real-world settings where sensor placement is hard to manage appropriately. Existing methods often rely on precise camera calibration or struggle with large perspective changes. To address these limitations, we propose ManiVID-3D, a novel 3D RL architecture designed for robotic manipulation, which learns view-invariant representations through self-supervised disentangled feature learning. The framework incorporates ViewNet, a lightweight yet effective module that automatically aligns point cloud observations from arbitrary viewpoints into a unified spatial coordinate system without the need for extrinsic calibration. Additionally, we develop an efficient GPU-accelerated batch rendering module capable of processing over 5000 frames per second, enabling large-scale training for 3D visual RL at unprecedented speeds. Extensive evaluation across 10 simulated and 5 real-world tasks demonstrates that our approach achieves a 40.6% higher success rate than state-of-the-art methods under viewpoint variations while using 80% fewer parameters. The system's robustness to severe perspective changes and strong sim-to-real performance highlight the effectiveness of learning geometrically consistent representations for scalable robotic manipulation in unstructured environments.