3D是英文“Three Dimensions”的简称,中文是指三维、三个维度、三个坐标,即有长、有宽、有高,换句话说,就是立体的,是相对于只有长和宽的平面(2D)而言。

VIP内容

题目: PolyGen: An Autoregressive Generative Model of 3D Meshes

摘要:

多边形网格是三维几何的一种有效表现形式,在计算机图形学、机器人技术和游戏开发中具有重要意义。现有的基于学习的方法避免了使用3D网格的挑战,而是使用与神经结构和训练方法更兼容的替代对象表示。提出了一种直接对网格建模的方法,利用基于变换的结构对网格顶点和面进行顺序预测。我们的模型可以对一系列输入进行条件设置,包括类对象、体素和图像,因为模型是概率性的,所以它可以生成在模糊场景中捕获不确定性的样本。我们证明了该模型能够产生高质量、可用的网格,并为网格建模任务建立了对数似然基准。我们还根据不同的方法评估了表面重建的条件模型,并在没有直接训练的情况下展示了竞争性的表现。

成为VIP会员查看完整内容
0
18

最新论文

In this work, we propose a novel two-stage framework for the efficient 3D point cloud object detection. Instead of transforming point clouds into 2D bird eye view projections, we parse the raw point cloud data directly in the 3D space yet achieve impressive efficiency and accuracy. To achieve this goal, we propose dynamic voxelization, a method that voxellizes points at local scale on-the-fly. By doing so, we preserve the point cloud geometry with 3D voxels, and therefore waive the dependence on expensive MLPs to learn from point coordinates. On the other hand, we inherently still follow the same processing pattern as point-wise methods (e.g., PointNet) and no longer suffer from the quantization issue like conventional convolutions. For further speed optimization, we propose the grid-based downsampling and voxelization method, and provide different CUDA implementations to accommodate to the discrepant requirements during training and inference phases. We highlight our efficiency on KITTI 3D object detection dataset with 75 FPS and on Waymo Open dataset with 25 FPS inference speed with satisfactory accuracy.

0
0
下载
预览
Top