Knowledge Commons of Institute of Automation,CAS
DefFusion: Deformable Multimodal Representation Fusion for 3D Semantic Segmentation | |
Xu RT(许镕涛)![]() ![]() ![]() ![]() ![]() ![]() ![]() | |
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 | 否 |
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 |
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。
修改评论