Reconstructing 3D human body shapes from 3D partial textured scans remains a fundamental task for many computer vision and graphics applications -- e.g., body animation, and virtual dressing. We propose a new neural network architecture for 3D body shape and high-resolution texture completion -- BCom-Net -- that can reconstruct the full geometry from mid-level to high-level partial input scans. We decompose the overall reconstruction task into two stages - first, a joint implicit learning network (SCom-Net and TCom-Net) that takes a voxelized scan and its occupancy grid as input to reconstruct the full body shape and predict vertex textures. Second, a high-resolution texture completion network, that utilizes the predicted coarse vertex textures to inpaint the missing parts of the partial 'texture atlas'. A Thorough experimental evaluation on 3DBodyTex.V2 dataset shows that our method achieves competitive results with respect to the state-of-the-art while generalizing to different types and levels of partial shapes. The proposed method has also ranked second in the SHARP 2022 Challenge1-Track1.
翻译:从 3D 部分纹理扫描 重建 3D 人体形状 从 3D 部分纹理扫描 重建 3D 人体形状仍然是许多计算机视觉和图形应用 -- -- 例如身体动画和虚拟敷料 -- -- 的一项基本任务。我们提议为 3D 身体形状和高分辨率纹理完成 -- -- BCom-Net -- -- 建立一个新的神经网络架构,可以将完整的几何从中层重建到高级部分输入扫描。我们将总体重建任务分为两个阶段 -- -- 首先,一个联合隐含学习网络(SCom-Net 和 TCom-Net Net), 将一个氧化扫描及其占用网作为重建整个身体形状和预测螺旋纹理的投入。第二,一个高分辨率纹理完成网络,利用预测的神经垂直纹理纹理纹理将部分“ Textlas” 的缺失部分重新粉饰。一个关于 3DbodyTex.V2 数据集的索罗夫实验性评价显示,我们的方法在状态上取得了竞争性的结果,同时将一般地归纳为不同类型和部分形状的层次。提议的方法也在SHAR1 20RF 中排名中排名 。