什么构成了用于零样本立体匹配的优质合成训练数据?
What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
对做双目立体匹配或任何需要合成训练数据的视觉任务,这篇论文给出了程序化生成器的参数消融方法论:逐参数扫描并测量零样本基准性能,可直接迁移到光流、深度估计等任务的数据集设计上。
原文依据 We investigate the design space of synthetic datasets by varying the parameters of a procedural dataset generator
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论合成数据集是训练立体匹配网络的关键要素,但什么样的立体数据集才算有效,这一问题仍缺乏充分探索。我们通过改变程序化数据集生成器的参数来考察合成数据集的设计空间,并利用标准基准报告其对零样本立体匹配性能的影响。我们收集最佳设置并构建了一个大规模数据集,以此验证了上述发现。仅在该数据集上训练,性能即优于在多个广泛使用数据集的混合上训练,并与在 FoundationStereo 数据集上训练相当,同时还额外提供了开源生成代码及配套的参数分析,以支持后续研究。我们开源了该系统,以推动程序化立体数据集的进一步研究。
英文原文摘要 848 字符
Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. We investigate the design space of synthetic datasets by varying the parameters of a procedural dataset generator, and report the effects on zero-shot stereo matching performance using standard benchmarks. We validate our findings by collecting the best settings and creating a large-scale dataset. Training only on this dataset achieves better performance than training on a mixture of widely used datasets, and is competitive with training on the FoundationStereo dataset, with the additional benefit of open-source generation code and an accompanying parameter analysis to enable further research. We open-source our system to enable further research on procedural stereo datasets.