用单张图高效重建3D物体，速度超150帧每秒
Single-View 3D Reconstruction via SO(2)-Equivariant Gaussian Sculpting Networks
- 基于SO(2)等变性设计高通量高斯雕刻网络
- 单视图输入生成几何与纹理的高精度高斯点云
- 适合机器人抓取等实时3D感知场景
本文提出一种SO(2)-等变的高斯雕刻网络（GSNs），用于从单张图像实现3D物体重建。该方法以单视角图像为输入，生成描述物体几何与纹理的高斯点云表示。通过共享特征提取器解码高斯的颜色、协方差、位置和不透明度，模型达到超过150FPS的极高速率。实验表明，使用多视图渲染损失可高效训练，且重建质量可媲美昂贵的扩散模型。在多个基准测试中验证了有效性，并展示了其在以物体为中心的机器人抓取任务中的应用潜力。
原文摘要 · Abstract (English)
This paper introduces SO(2)-Equivariant Gaussian Sculpting Networks (GSNs) as an approach for SO(2)-Equivariant 3D object reconstruction from single-view image observations. GSNs take a single observation as input to generate a Gaussian splat representation describing the observed object's geometry and texture. By using a shared feature extractor before decoding Gaussian colors, covariances, positions, and opacities, GSNs achieve extremely high throughput (>150FPS). Experiments demonstrate that GSNs can be trained efficiently using a multi-view rendering loss and are competitive, in quality, with expensive diffusion-based reconstruction algorithms. The GSN model is validated on multiple benchmark experiments. Moreover, we demonstrate the potential for GSNs to be used within a robotic manipulation pipeline for object-centric grasping.
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。