Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules. However, this approach is constrained by higher memory expenses and limited representation capabilities. In this paper, we introduce a novel dynamic grid optimization method for high-fidelity 3D surface reconstruction that incorporates both RGB and depth observations. Rather than treating each voxel equally, we optimize the process by dynamically modifying the grid and assigning more finer-scale voxels to regions with higher complexity, allowing us to capture more intricate details. Furthermore, we develop a scheme to quantify the dynamic subdivision of voxel grid during optimization without requiring any priors. The proposed approach is able to generate high-quality 3D reconstructions with fine details on both synthetic and real-world data, while maintaining computational efficiency, which is substantially faster than the baseline method NeuralRGBD.
翻译:直接优化多分辨率体素网格上的插值特征已经被证明是一种更高效的替代MLP-like模块的方法。然而,这种方法受到更高的内存开销和有限的表示能力的限制。在本文中,我们提出了一种新的动态网格优化方法,用于高保真度的三维表面重构,结合了RGB和深度观测。我们并不将每个体素视为相等的,而是通过动态修改网格并将更细粒度的体素分配给更复杂的区域来优化过程,从而使我们捕捉更复杂的细节。此外,我们还开发了一种方案,在优化过程中量化体素网格的动态分割,而无需任何先验知识。所提出的方法能够基于合成和实际数据生成高品质的三维重构,在保持计算效率的条件下,比基线方法NeuralRGBD快得多。