# PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications

arXiv: https://arxiv.org/abs/2512.01383 · HTML: https://mlsanity.com/paper/2512.01383/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 39 of its 54 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 30 of 39)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [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)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://mlsanity.com/paper/2109.00179/) (2021)
- [RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins](https://mlsanity.com/paper/2504.13059/) (2025)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture](https://mlsanity.com/paper/2409.02889/) (2024)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [3DV: 3D Dynamic Voxel for Action Recognition in Depth Video](https://mlsanity.com/paper/2005.05501/) (2020)
- [Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2208.00281/) (2022)
- [Learning Human-to-Robot Handovers from Point Clouds](https://mlsanity.com/paper/2303.17592/) (2023)
- [Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning](https://mlsanity.com/paper/2212.05330/) (2022)
- [PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis](https://mlsanity.com/paper/2405.15463/) (2024)
- [No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces](https://mlsanity.com/paper/2203.11113/) (2022)
- [Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds](https://mlsanity.com/paper/2010.00824/) (2020)
- [Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models](https://mlsanity.com/paper/2409.07163/) (2024)
- [PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos](https://mlsanity.com/paper/2305.04075/) (2023)
- [Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos](https://mlsanity.com/paper/2308.09245/) (2023)
- [Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection](https://mlsanity.com/paper/1911.10280/) (2019)
- [Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos](https://mlsanity.com/paper/2308.09247/) (2023)

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

- [Diffusion Masked Pretraining for Dynamic Point Cloud](https://mlsanity.com/paper/2605.03639/) (2026)

## Abstract (arXiv)

Understanding dynamic 4D environments-3D space evolving over time-is critical for robotic and interactive systems. These applications demand systems that can process streaming point cloud video in real-time, often under resource constraints, while also benefiting from past and present observations when available. However, current 4D backbone networks rely heavily on spatiotemporal convolutions and Transformers, which are often computationally intensive and poorly suited to real-time applications. We propose PointNet4D, a lightweight 4D backbone optimized for both online and offline settings. At its core is a Hybrid Mamba-Transformer temporal fusion block, which integrates the efficient state-space modeling of Mamba and the bidirectional modeling power of Transformers. This enables PointNet4D to handle variable-length online sequences efficiently across different deployment scenarios. To enhance temporal understanding, we introduce 4DMAP, a frame-wise masked auto-regressive pretraining strategy that captures motion cues across frames. Our extensive evaluations across 9 tasks on 7 datasets, demonstrating consistent improvements across diverse domains. We further demonstrate PointNet4D's utility by building two robotic application systems: 4D Diffusion Policy and 4D Imitation Learning, achieving substantial gains on the RoboTwin and HandoverSim benchmarks.