文献类型：期刊文献

英文题名：CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism

作者：Zhu, Ziming[1]; Zhu, Yu[1]; Chen, Jiahao[1]; Ling, Xiaofeng[1,2]; Chen, Huanlei[3]; Sun, Lihua[1]

机构：[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China; [2] Shanghai Key Laboratory of Intelligent Sensing and Detection Technology, East China University of Science and Technology, Shanghai, China; [3] Shanghai Motor Vehicle Inspection Certification & Tech Innovation Center Co., Ltd., Shanghai, China

年份：2025

卷号：267

起止页码：80480

外文期刊名：Proceedings of Machine Learning Research

收录：EI(收录号：20254919636715)

语种：英文

外文关键词：Autonomous vehicles - Latent semantic analysis - Object detection - Semantic Segmentation - Semantics - State space methods - Three dimensional computer graphics

摘要：Recently, image-based 3D semantic occupancy prediction has become a hot topic in 3D scene understanding for autonomous driving. Compared with the bounding box form of 3D object detection, the ability to describe the fine-grained contours of any obstacles in the scene is the key insight of voxel occupancy representation, which facilitates subsequent tasks of autonomous driving. In this work, we propose CSV-Occ to address the following two challenges: (1) Existing methods fuse temporal information based on the attention mechanism, but are limited by high complexity. We extend the state space model to support multi-input sequence interaction and conduct temporal modeling in a cascaded architecture, thereby reducing the computational complexity from quadratic to linear. (2) Existing methods are limited by semantic ambiguity, resulting in the centers of foreground objects often being predicted as empty voxels. We enable the model to explicitly vote for the instance center to which the voxels belong and spontaneously learn to utilize the other voxel features of the same instance to update the semantics of the internal vacancies of the objects from coarse to fine. Experiments on the Occ3D-nuScenes dataset show that our method achieves state-of-the-art in camera-based 3D semantic occupancy prediction and also performs well on lidar point cloud semantic segmentation on the nuScenes dataset. Code will be available at. ? 2025 by the author(s).