用一段探索数据训练点云编码器,实现无需预设类别的动态场景物体关联
BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding
- 基于单段探索数据训练无类别依赖的点云编码器
- 在动态场景中实现95%成功率的物体关联,较基线提升7%
- 融合视觉语言模型语义能力,适合长期动态环境机器人应用
动态场景理解仍是机器人应用中的持续挑战。早期方法通过掩码或追踪特定类别来缓解短期动态物体对相机位姿估计的干扰,但难以适应长期场景变化。近期工作利用合成数据训练神经网络解决长期动态环境中的物体关联问题,但仍依赖预设物体形状和类别。其他方法结合视觉、几何或语义启发式规则,但鲁棒性不足。本文提出BYE,一种无类别、面向场景的点云编码器,无需预设类别、形状先验或大规模关联数据集。仅需单段探索数据即可训练,能高效完成动态变化场景中的物体关联。我们进一步提出集成方案,结合视觉语言模型(VLMs)的语义优势与BYE的场景专长,在物体关联任务中实现7%性能提升,成功率达95%。代码与数据集见https://byencoder.github.io。
原文摘要 · Abstract (English)
Dynamic scene understanding remains a persistent challenge in robotic applications. Early dynamic mapping methods focused on mitigating the negative influence of short-term dynamic objects on camera motion estimation by masking or tracking specific categories, which often fall short in adapting to long-term scene changes. Recent efforts address object association in long-term dynamic environments using neural networks trained on synthetic datasets, but they still rely on predefined object shapes and categories. Other methods incorporate visual, geometric, or semantic heuristics for the association but often lack robustness. In this work, we introduce BYE, a class-agnostic, per-scene point cloud encoder that removes the need for predefined categories, shape priors, or extensive association datasets. Trained on only a single sequence of exploration data, BYE can efficiently perform object association in dynamically changing scenes. We further propose an ensembling scheme combining the semantic strengths of Vision Language Models (VLMs) with the scene-specific expertise of BYE, achieving a 7% improvement and a 95% success rate in object association tasks. Code and dataset are available at https://byencoder.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。