CVDec 13, 2022

Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation

arXiv:2212.06682v14 citationsh-index: 40
Originality Incremental advance
AI Analysis

This addresses a bottleneck in multi-view 3D scene understanding for applications like robotics and autonomous driving, though it appears incremental.

The paper tackles the problem of fusing 2D image features with 3D point cloud features for 3D semantic segmentation by proposing a unidirectional projection method instead of bidirectional approaches, achieving superior performance on the ScanNetv2 benchmark.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes