PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications
This work addresses the need for efficient real-time 4D perception in robotics, offering a novel method that is incremental in combining existing techniques for improved performance.
The paper tackles the problem of processing dynamic 4D point cloud videos for robotic applications by proposing PointNet4D, a lightweight backbone that integrates Mamba and Transformer models, achieving consistent improvements across 9 tasks on 7 datasets and substantial gains in robotic systems like 4D Diffusion Policy and 4D Imitation Learning.
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.