Shadow Constrained DEM Refinement Based on Differentiable Rendering

Digital elevation models (DEMs) are the fundamental for modeling and analyzing spatial topographic information in geographic information system, 3D video games, and many other fields. However, due to various terrain factors in data acquisition, open access datasets often contain inaccurate data or miss data, leading to undesirable models. This paper proposes a terrain refinement method based on shadow constraints by taking full advantages of differentiable rendering enabled efficient optimization. To be specific, we introduce an iterative approach to optimize shadow masks from satellite images based on differentiable rendering, which provides extra geometric clues for further terrain refinement. Thereafter, we propose to synthesize high-quality data in a randomization manner via differentiable renderer to expose the latent correlation between shadow distribution and terrain geometry, and generalize to real-world DEMs. Moreover, structure lines extracted from forward rendering results are also utilized to provide comprehensive geometric constraints for terrains. Extensive experiments demonstrate the effectiveness of our proposed methods.