LoCoFormer: Rethinking Local Geometric and Semantic Context Representation for Point Cloud Transformers

Synergistically capturing local geometric structures and semantic features remains a critical challenge in 3D point cloud analysis. Recent attempts to integrate local point operators into point cloud Transformers have made impressive progress, yet they still struggle to fully exploit local contexts. In this paper, we present LoCoFormer, an effective framework for comprehensive local geometric and semantic representation. Specifically, we identify the limitations of conventional Softmax attention and propose Bilateral Context Attention (BCA). BCA adopts delicate geometric and semantic context branches to separately capture spatial structures and implicit features, and utilizes a bilateral fusion mechanism to modulate attention weights and provide geometric priors, establishing enhanced local contextual dependencies. Furthermore, motivated by the observation that architectural design affects information acquisition and propagation, we modernize the network architecture from three aspects: $\text{Spatial Proximity}$, $\text{Raw-point Embedding}$, and $\text{Pooling Strategy}$, which respectively determine receptive field size, feature initialization, and spatial alignment, thereby improving local context representation. Experimental results demonstrate that LoCoFormer achieves superior performance across multiple challenging benchmarks, including ModelNet40 for shape classification and S3DIS, ScanNet v2, and ScanNet200 for semantic segmentation.