English

Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation

Computer Vision and Pattern Recognition 2025-02-07 v1

Abstract

3D instance segmentation aims to predict a set of object instances in a scene and represent them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to their elegant pipelines, reduced manual selection of geometric properties, and superior performance. However, transformer-based methods fail to simultaneously maintain strong position and content information during query initialization. Additionally, due to supervision at each decoder layer, there exists a phenomenon of object disappearance with the deepening of layers. To overcome these hurdles, we introduce Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation (BFL). Specifically, an Agent-Interpolation Initialization Module is designed to generate resilient queries capable of achieving a balance between foreground coverage and content learning. Additionally, a Hierarchical Query Fusion Decoder is designed to retain low overlap queries, mitigating the decrease in recall with the deepening of layers. Extensive experiments on ScanNetV2, ScanNet200, ScanNet++ and S3DIS datasets demonstrate the superior performance of BFL.

Keywords

Cite

@article{arxiv.2502.04139,
  title  = {Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation},
  author = {Jiahao Lu and Jiacheng Deng and Tianzhu Zhang},
  journal= {arXiv preprint arXiv:2502.04139},
  year   = {2025}
}

Comments

Under review

R2 v1 2026-06-28T21:34:54.387Z