The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) - an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.
翻译:单眼 2D 图像的非硬化 3D 表面回归的现有方法大多需要多个框架的物体模板或点轨迹作为输入,并且仍然远非实时处理率。 在这项工作中,我们展示了Ismo-GAN(Ismo-GAN)-一种从单一图像直接重建3D的方法,在轻量合成数据集上以对称方式培训了变形模型。 IsMo-GAN(Ismo-GAN) 将不同照明下的真实图像、相机配置、纹理和阴影在250赫兹以上的地方重建了表面。在多个实验中,它始终在重建精度、运行时间、对未知表面的概括性以及隔离性等方面优于几种方法。与最新工艺相比,我们将重建错误减少10-30%,包括无纹理案例和我们表面质量较少的手工艺品质量。