Matching-Free Depth Recovery from Structured Light
This work addresses depth recovery for structured light systems, offering a faster and more accurate alternative to matching-based techniques, though it is incremental as it builds on existing volume rendering approaches.
The paper tackles depth estimation from monocular structured light images without relying on image matching, using a density voxel grid trained via self-supervised differentiable volume rendering, resulting in a 30% reduction in average depth errors and training three times faster than previous methods.
We introduce a novel approach for depth estimation using images obtained from monocular structured light systems. In contrast to many existing methods that depend on image matching, our technique employs a density voxel grid to represent scene geometry. This grid is trained through self-supervised differentiable volume rendering. Our method leverages color fields derived from the projected patterns in structured light systems during the rendering process, facilitating the isolated optimization of the geometry field. This innovative approach leads to faster convergence and high-quality results. Additionally, we integrate normalized device coordinates (NDC), a distortion loss, and a distinctive surface-based color loss to enhance geometric fidelity. Experimental results demonstrate that our method outperforms current matching-based techniques in terms of geometric performance in few-shot scenarios, achieving an approximately 30% reduction in average estimated depth errors for both synthetic scenes and real-world captured scenes. Moreover, our approach allows for rapid training, being approximately three times faster than previous matching-free methods that utilize implicit representations.