用少量图像生成物体几何表示，实现零样本快速感知
Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception
- 通过少数模板图生成含语义与几何信息的稀疏点云
- 单网络完成检测、分割、6自由度位姿估计，性能达顶尖水平
- 无需重训练或标定，适合快速部署新物体感知
我们提出神经记忆物体（NeMO），一种新型以物体为中心的表示方法，仅需少量包含目标物体的RGB模板视图，即可在无需任何相机参数或目标数据微调的情况下，实现对未见物体的检测、分割和6自由度位姿估计。该方法首先通过编码器利用学习到的隐式距离函数（UDF）生成富含语义与几何信息的稀疏点云；随后解码器结合物体编码与查询图像，输出多种密集预测结果。大量实验表明，该方法在BOP基准多个数据集和感知任务上均达到竞争性及领先水平，验证了其通用性。通过将物体信息外置于NeMO并使用单一网络完成多任务感知，显著提升了与新物体交互的可扩展性与效率，实现无需重训练的快速物体上线。
原文摘要 · Abstract (English)
We present Neural Memory Object (NeMO), a novel object-centric representation that can be used to detect, segment and estimate the 6DoF pose of objects unseen during training using RGB images. Our method consists of an encoder that requires only a few RGB template views depicting an object to generate a sparse object-like point cloud using a learned UDF containing semantic and geometric information. Next, a decoder takes the object encoding together with a query image to generate a variety of dense predictions. Through extensive experiments, we show that our method can be used for few-shot object perception without requiring any camera-specific parameters or retraining on target data. Our proposed concept of outsourcing object information in a NeMO and using a single network for multiple perception tasks enhances interaction with novel objects, improving scalability and efficiency by enabling quick object onboarding without retraining or extensive pre-processing. We report competitive and state-of-the-art results on various datasets and perception tasks of the BOP benchmark, demonstrating the versatility of our approach. https://github.com/DLR-RM/nemo
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。