Towards Generalising Neural Implicit Representations
Towards Generalising Neural Implicit Representations
复制标题
DOI：
--
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Theo W. Costain;V. Prisacariu
中科院分区：
文献类型：
--
作者：
Theo W. Costain;V. Prisacariu
与传统格式相比，神经隐式表示在有效存储3D数据方面显示出实质性的改进。然而，现有工作的重点主要是储存和随后的重建。在这项工作中，我们表明，与传统任务一起训练重建任务的神经表征可以产生更通用的编码，允许与单一任务训练相同质量的重建，同时与单一任务编码相比，改善了传统任务的结果。我们重新制定了语义分割任务，为隐式表示上下文创建了一个更具代表性的任务，并通过对重构、分类和分割的多任务实验表明，我们的方法学习到了丰富的编码特征，这些编码允许每个任务具有相同的性能。
Neural implicit representations have shown substantial improvements in efficiently storing 3D data, when compared to conventional formats. However, the focus of existing work has mainly been on storage and subsequent reconstruction. In this work, we show that training neural representations for reconstruction tasks alongside conventional tasks can produce more general encodings that admit equal quality reconstructions to single task training, whilst improving results on conventional tasks when compared to single task encodings. We reformulate the semantic segmentation task, creating a more representative task for implicit representation contexts, and through multi-task experiments on reconstruction, classification, and segmentation, show our approach learns feature rich encodings that admit equal performance for each task.