Capturing general deforming scenes from monocular RGB video is crucial for many computer graphics and vision applications. However, current approaches suffer from drawbacks such as struggling with large scene deformations, inaccurate shape completion or requiring 2D point tracks. In contrast, our method, Ub4D, handles large deformations, performs shape completion in occluded regions, and can operate on monocular RGB videos directly by using differentiable volume rendering. This technique includes three new in the context of non-rigid 3D reconstruction components, i.e., 1) A coordinate-based and implicit neural representation for non-rigid scenes, which in conjunction with differentiable volume rendering enables an unbiased reconstruction of dynamic scenes, 2) a proof that extends the unbiased formulation of volume rendering to dynamic scenes, and 3) a novel dynamic scene flow loss, which enables the reconstruction of larger deformations by leveraging the coarse estimates of other methods. Results on our new dataset, which will be made publicly available, demonstrate a clear improvement over the state of the art in terms of surface reconstruction accuracy and robustness to large deformations.
翻译:对许多计算机图形和视觉应用而言,单镜 RGB 视频获取一般变形场景至关重要,但是,目前的方法存在缺点,例如与大场景变形、不准确的形状完成或需要2D点轨迹作斗争。相比之下,我们的方法Ub4D,处理大变形,在隐蔽区域进行形状完成,并且可以通过使用可变体积的粗略估计直接使用单镜 RGB 视频操作。这一技术包括非硬3D 重建组成部分方面的三个新技术,即:(1) 非硬形场景的协调基和隐含神经表层,与可变体积相结合,使得能够对动态场景进行公正的重建;(2) 证据,将无偏向的体积形状扩展到动态场景;(3) 新的动态场景流动损失,通过利用其他方法的粗微估计,使得更大的变形的重建得以进行。我们将公开提供的新的数据集的结果表明,在地表重建准确性和坚固度方面,在大变形方面,比艺术状况有明显改善。