用简单规则生成高质量多视角立体训练数据，效果超越大量人工标注数据。
SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo
- 基于NURBS和基础纹理规则，全自动生成合成图像
- 8000张图效果优于同等规模人工数据，35万张图媲美69万张人工数据
- 适合需要大规模合成数据的三维重建研究者使用
本文探索了多视角立体（MVS）中过程化规则的设计空间。我们提出SimpleProc：一种完全基于少量规则的合成数据生成器，利用非均匀有理样条（NURBS）以及基本位移和纹理模式生成训练数据。在仅8000张图像的规模下，该方法性能优于同等规模的人工采集图像（来自游戏和真实物体）。当扩展至352,000张图像时，其表现可与在超过692,000张人工标注图像上训练的模型相当，且在多个基准测试中实现超越。代码与数据集已公开于https://github.com/princeton-vl/SimpleProc。
原文摘要 · Abstract (English)
In this paper, we explore the design space of procedural rules for multi-view stereo (MVS). We demonstrate that we can generate effective training data using SimpleProc: a new, fully procedural generator driven by a very small set of rules using Non-Uniform Rational Basis Splines (NURBS), as well as basic displacement and texture patterns. At a modest scale of 8,000 images, our approach achieves superior results compared to manually curated images (at the same scale) sourced from games and real-world objects. When scaled to 352,000 images, our method yields performance comparable to--and in several benchmarks, exceeding--models trained on over 692,000 manually curated images. The source code and the data are available at https://github.com/princeton-vl/SimpleProc.
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。