DefFusion: Deformable Multimodal Representation Fusion for 3D Semantic Segmentation
Xu RT(许镕涛); Changwei Wang; Duzhen Zhang; Man Zhang; Shibiao Xu; Weiliang Meng; Xiaopeng Zhang
2024-05
会议名称IEEE International Conference on Robotics and Automation
会议日期2024-5
会议地点日本横滨
摘要
The complementarity between camera and LiDAR data makes fusion methods a promising approach to improve 3D semantic segmentation performance. Recent transformer-based methods have also demonstrated superiority in segmentation. However, multimodal solutions incorporating transformers are underexplored and face two key inherent difficulties: over- attention and noise from different modal data. To overcome these challenges, we propose a Deformable Multimodal Representation Fusion (DefFusion) framework consisting mainly of a Deformable Representation Fusion Transformer and Dynamic Representation Augmentation Modules. The Deformable Representation Fusion Transformer introduces the deformable mechanism in multimodal fusion, avoiding over- attention and improving efficiency by adaptively modeling a 2D key/value set for a given 3D query, thus enabling multimodal fusion with higher flexibility. To enhance the 2D representation and 3D representation, the Dynamic Representation Enhancement Module is proposed to dynamically remove noise in the input representation via Dynamic Grouped Representation Generation and Dynamic Mask Generation. Extensive experiments validate that our model achieves the best 3D semantic segmentation performance on SemanticKITTI and NuScenes benchmarks.
七大方向——子方向分类图像视频处理与分析
国重实验室规划方向分类环境多维感知
是否有论文关联数据集需要存交
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/57545
专题多模态人工智能系统全国重点实验室_三维可视计算
作者单位Institute of Automation,Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Xu RT,Changwei Wang,Duzhen Zhang,et al. DefFusion: Deformable Multimodal Representation Fusion for 3D Semantic Segmentation[C],2024.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
ICRA2024_DefFusion.p(4813KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xu RT(许镕涛)]的文章
[Changwei Wang]的文章
[Duzhen Zhang]的文章
百度学术
百度学术中相似的文章
[Xu RT(许镕涛)]的文章
[Changwei Wang]的文章
[Duzhen Zhang]的文章
必应学术
必应学术中相似的文章
[Xu RT(许镕涛)]的文章
[Changwei Wang]的文章
[Duzhen Zhang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: ICRA2024_DefFusion.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。