NeRFifyMesh:从带纹理网格综述优化神经辐射场:用于机器人场景构建
NeRFifyMesh: Optimizing Neural Radiance Fields from Textured Meshes for Robotics Scene Building
Nillan Nimal · Mahboubeh Asadi · Sajad Saeedi
中文摘要
在机器人学中,场景表征对于理解环境与交互至关重要。神经辐射场(NeRF)及其变体作为一种新表征方法,开辟了新的研究前沿。在语义建图与仿真等应用中,机器人研究者希望使用多个 NeRF 模型(每个代表一个物体)来构建场景。尽管已存在大量三维网格模型数据集,但迫切需要工具将这些资产转换为 NeRF 模型,以加速算法开发与测试。该论文提出了一种新流程,通过采样网格几何与纹理人工生成基于点的辐射场作为监督真值,从而将现有网格模型转换为 NeRF 表征。该方法无需基于相机的采样,也无须对原始网格进行多视角渲染来训练 NeRF 模型。大量基准测试表明,该方法在渲染质量上与基线相当。此外,通过构建统一的 NeRF 场景并结合提取的几何进行碰撞仿真,展示了该表征的应用方式。
关键要点
- 01问题:机器人场景构建需要大量 NeRF 模型,但已有海量三维网格资产缺乏向 NeRF 的转换工具
- 02方法:通过采样网格几何与纹理人工生成基于点的辐射场作为监督真值,直接训练 NeRF,跳过多视角图像采集与渲染
- 03结果:渲染质量与基线方法相当,且能构建统一 NeRF 场景
- 04应用:利用统一 NeRF 场景与提取的碰撞几何进行碰撞仿真,服务于机器人测试
- 05贡献:降低 NeRF 训练对多视角图像采集的依赖,加速机器人算法开发与测试流程
解读
尚无解读。
原始英文摘要
arXiv:2610.10387v1 Announce Type: new Abstract: In robotics, scene representation plays a pivotal role in understanding and interacting with the environment. The advent of Neural Radiance Fields (NeRF) and its variants, as a novel representation, has opened a new frontier of research. In applications such as semantic mapping and simulation, roboticists aim to build scenes using multiple NeRF models, each representing an object. While extensive datasets of 3D mesh models already exist, there is an urgent need to develop tools to convert these assets to NeRF models for rapid algorithm development and testing. This paper presents a new pipeline for converting existing mesh models to NeRF representations by artificially generating a ground truth point-based radiance field through sampling mesh geometry and texture. This approach alleviates the need for camera-based sampling or rendering multi-view images of the original mesh to train the NeRF model. Extensive benchmarking demonstrates that our method yields comparable rendering quality to the baselines. Additionally, the application of this representation is shown by constructing unified NeRF scenes and performing collision simulations with extracted geometry.