LION: Linear Group RNN for 3D Object Detection in Point Clouds

TL;DR

LION introduces a window-based linear group RNN framework for 3D object detection in point clouds, achieving state-of-the-art results by enhancing spatial modeling and densifying features in sparse data.

Contribution

The paper proposes a novel linear group RNN framework with spatial descriptors and densification strategies for improved 3D object detection in sparse point clouds.

Findings

LION achieves state-of-the-art performance on Waymo, nuScenes, Argoverse V2, and ONCE datasets.

The framework effectively integrates various linear RNN operators like Mamba, RWKV, and RetNet.

The method supports multiple linear RNN variants on the KITTI dataset for quick deployment.

Abstract

The benefit of transformers in large-scale 3D point cloud perception tasks, such as 3D object detection, is limited by their quadratic computation cost when modeling long-range relationships. In contrast, linear RNNs have low computational complexity and are suitable for long-range modeling. Toward this goal, we propose a simple and effective window-based framework built on LInear grOup RNN (i.e., perform linear RNN for grouped features) for accurate 3D object detection, called LION. The key property is to allow sufficient feature interaction in a much larger group than transformer-based methods. However, effectively applying linear group RNN to 3D object detection in highly sparse point clouds is not trivial due to its limitation in handling spatial modeling. To tackle this problem, we simply introduce a 3D spatial feature descriptor and integrate it into the linear group RNN operators to enhance their spatial features rather than blindly increasing the number of scanning orders for voxel features. To further address the challenge in highly sparse point clouds, we propose a 3D voxel generation strategy to densify foreground features thanks to linear group RNN as a natural property of auto-regressive models. Extensive experiments verify the effectiveness of the proposed components and the generalization of our LION on different linear group RNN operators including Mamba, RWKV, and RetNet. Furthermore, it is worth mentioning that our LION-Mamba achieves state-of-the-art on Waymo, nuScenes, Argoverse V2, and ONCE dataset. Last but not least, our method supports kinds of advanced linear RNN operators (e.g., RetNet, RWKV, Mamba, xLSTM and TTT) on small but popular KITTI dataset for a quick experience with our linear RNN-based framework.