A Multi-Perspective Recursive Slice Framework with Cross-Slice Attention for Plant Point Cloud Instance Segmentation

Abstract

Instance segmentation of plant point clouds is challenging due to intricate structures, non-uniform density, and large intra-class variation. Conventional methods often suffer from blurred boundaries, instance adhesion, and insufficient coupling of semantic and instance features. To address these issues, this paper proposes MPRSF-CSA, a novel network integrating recursive slice-based feature extraction with an attention-embedding mechanism. The method first transforms disordered point clouds into ordered sequences via a multi-directional recursive slicing strategy and models inter-slice dependencies using BiLSTM. Parallel decoding branches for semantic and instance segmentation are constructed, and a core attention-embedding module facilitates bidirectional fusion of semantic and instance features. Instance segmentation is achieved via clustering and semantic-aware optimization. Experiments on two public datasets demonstrate that MPRSF-CSA outperforms existing approaches in segmentation accuracy, boundary preservation, and adaptability to complex plant scenes.

Code and data availability

The paper evaluates on two public plant point cloud benchmarks (Soybean-MVS and PP3D), but both are cited prior datasets [43,44], not assets released by this paper's authors. No author code, trained models, or data deposit with an explicit public URL appears in the supplied blocks.

No evidence-backed public reproduction asset is currently recorded.