Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection

Jin Gao, Weiming Hu, Zhipeng Zhang, Low High, Hanshi Wang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• AutoLab-SAI-SJTU/MambaFusion

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present the first work demonstrating that a pure Mamba block can achieve efficient Dense Global Fusion, meanwhile guaranteeing top performance for camera-LiDAR multi-modal 3D object detection. Our motivation stems from the observation that existing fusion strategies are constrained by their inability to simultaneously achieve efficiency, long-range modeling, and retaining complete scene information. Inspired by recent advances in statespace models (SSMs) [8] and linear attention [35,43], we leverage their linear complexity and long-range modeling capabilities to address these challenges. However, this is non-trivial since our experiments reveal that simply adopting efficient linear-complexity methods does not necessarily yield improvements and may even degrade performance. We attribute this degradation to the loss of height information during multi-modal alignment, leading to deviations in sequence order. To resolve this, we propose height-fidelity LiDAR encoding that preserves precise height information through voxel compression in continuous space, thereby enhancing camera-LiDAR alignment. Subsequently, we introduce the Hybrid Mamba Block, which leverages the enriched height-informed features to conduct local and global contextual learning. By integrating these components, our method achieves state-of-the-art performance with the top-tire NDS score of 75.0 on the nuScenes [2] validation benchmark, even surpassing methods that utilize highresolution inputs. Meanwhile, our method maintains efficiency, achieving faster inference speed than most recent state-of-the-art methods. Code is available at https:// github.com/AutoLab-SAI-SJTU/MambaFusion

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2507.04369")
get_code_for_paper("2507.04369")
have("2507.04369")

Connect an agent — have() is free.