Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation
원문 초록
3D point clouds are rich in geometric structure information, while 2D images contain important and continuous texture information. Combining 2D information to achieve better 3D semantic segmentation has become mainstream in 3D scene understanding. Albeit the success, it still remains elusive how to fuse and process the cross-dimensional features from these two distinct spaces. Existing state-of-the-art usually exploit bidirectional projection methods to align the cross-dimensional features and realize both 2D & 3D semantic segmentation tasks. However, to enable bidirectional mapping, this framework often requires a symmetrical 2D-3D network structure, thus limiting the network's flexibility. Meanwhile, such dual-task settings may distract the network easily and lead to over-fitting in the 3D segmentation task. As limited by the network's inflexibility, fused features can only pass through a decoder network, which affects model performance due to insufficient depth. To alleviate these drawbacks, in this paper, we argue that despite its simplicity, projecting unidirectionally multi-view 2D deep semantic features into the 3D space aligned with 3D deep semantic features could lead to better feature fusion. On the one hand, the unidirectional projection enforces our model focused more on the core task, i.e., 3D segmentation; on the other hand, unlocking the bidirectional to unidirectional projection enables a deeper cross-domain semantic alignment and enjoys the flexibility to fuse better and complicated features from very different spaces. In joint 2D-3D approaches, our proposed method achieves superior performance on the ScanNetv2 benchmark for 3D semantic segmentation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Cross-Domain Few-Shot Semantic Segmentation
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images
PoSeg: Pose-Aware Refinement Network for Human Instance Segmentation
ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation
3D Semantic Segmentation of Modular Furniture using rjMCMC
토론
이 논문과 연결된 포럼 글이 아직 없습니다.