通过梯度匹配自动搜索最优损失函数，提升点云补全效果。
Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance
- 用梯度匹配自动寻找无需调参的加权切比雪夫距离损失
- 所提Landau加权损失在多个数据集上超越现有最优方法
- 适合关注3D点云补全与损失函数设计的研究者
三维点云提升了机器人对环境几何信息的感知能力，为抓取姿态检测、场景理解等下游任务奠定基础。然而，这些任务性能高度依赖输入数据质量，不完整点云会导致结果不佳甚至失败。近期基于深度学习的点云补全方法采用切比雪夫距离（CD）及其变体（如HyperCD），表明良好的梯度加权机制可显著提升性能。但这类基于CD的损失函数通常需要针对数据进行参数调优，对数据量大的任务耗时较长。为此，本文提出一种无需参数调优的加权CD损失家族搜索方案——损失蒸馏梯度匹配（Loss Distillation via Gradient Matching），通过模仿HyperCD与加权CD在反向传播中的学习行为，自动寻找优质候选损失函数。进一步提出新型双层优化公式，基于所选加权CD训练主干网络。实验发现：（1）合理加权函数下，加权CD性能可媲美HyperCD；（2）提出的兰道加权CD（Landau CD）在多个基准数据集上优于HyperCD，达到新最优结果。代码已开源。
原文摘要 · Abstract (English)
3D point clouds enhanced the robot's ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The performance of these tasks, though, heavily relies on the quality of data input, as incomplete can lead to poor results and failure cases. Recent training loss functions designed for deep learning-based point cloud completion, such as Chamfer distance (CD) and its variants (\eg HyperCD ), imply a good gradient weighting scheme can significantly boost performance. However, these CD-based loss functions usually require data-related parameter tuning, which can be time-consuming for data-extensive tasks. To address this issue, we aim to find a family of weighted training losses ({\em weighted CD}) that requires no parameter tuning. To this end, we propose a search scheme, {\em Loss Distillation via Gradient Matching}, to find good candidate loss functions by mimicking the learning behavior in backpropagation between HyperCD and weighted CD. Once this is done, we propose a novel bilevel optimization formula to train the backbone network based on the weighted CD loss. We observe that: (1) with proper weighted functions, the weighted CD can always achieve similar performance to HyperCD, and (2) the Landau weighted CD, namely {\em Landau CD}, can outperform HyperCD for point cloud completion and lead to new state-of-the-art results on several benchmark datasets. {\it Our demo code is available at \url{https://github.com/Zhang-VISLab/IROS2024-LossDistillationWeightedCD}.}
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。