Exploiting Continuity for Unsupervised Single Depth Map Super-Resolution

Depth map super-resolution (DSR) aims at reconstructing high-resolution depth maps from low-resolution input. Existing DSR methods rely on using the high-resolution RGB images as guidance and are typically trained in a supervised manner. However, obtaining well-aligned RGB-Depth pairs is challenging, and these approaches also suffer from texture over-transfer issues. To address these limitations, we propose the Implicit Depth Fitting Network (IDFN), a zero-shot, unsupervised framework that relies solely on a single low-resolution depth map. We formulate DSR as learning a resolution-independent continuous depth field. To accurately capture complex scene geometries, our framework combines Fourier feature encoding with periodic activation functions, effectively balancing smooth surface reconstruction with sharp edge preservation. Furthermore, we introduce a Dithering Strategy to model the sensor degradation process. This strategy enables the network to learn the underlying continuous signal from discrete area-integrated observations, effectively suppressing aliasing artifacts. Extensive experiments show that IDFN not only achieves performance comparable to state-of-the-art unsupervised approaches, but also yields results competitive with leading supervised approaches, demonstrating the effectiveness of our method.