We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised differentiable rendering. Unlike passive vision, where joint estimation of radiance and geometry fields is necessary, we capitalize on known radiance fields from projected patterns in structured light systems. This enables isolated optimization of the geometry field, ensuring convergence and network efficacy with fixed device positioning. To enhance geometric fidelity, we incorporate an additional color loss based on object surfaces during training. Real-world experiments demonstrate our method's superiority in geometric performance for few-shot scenarios, while achieving comparable results with increased pattern availability.

翻译：我们提出了一种新颖的多帧结构光深度估计技术，该技术利用三维空间的神经隐式表示。我们的方法采用神经有符号距离场（SDF），并通过自监督可微渲染进行训练。与被动视觉不同，被动视觉中需要联合估计辐射场和几何场，而我们的方法利用了结构光系统中投影图案的已知辐射场，从而能够独立优化几何场，确保在固定设备位置下的收敛性和网络效能。为增强几何保真度，我们在训练过程中引入了一项基于物体表面的额外颜色损失。真实世界实验表明，在少样本场景下，我们的方法在几何性能上表现出优越性，而在增加图案可用性时仍能取得相当的结果。