Intensity-guided edge-preserving depth upsampling through weighted L0 gradient minimization

- Intensity-guided edge-preserving depth upsampling.
- Weighted L0 gradient minimization.
- Alternating minimization and half-quadratic splitting.
- Suppressing edge blurring and texture copying artifacts.

Depth is an important visual cue to perceive real-world scenes. Although a time-of-flight (ToF) depth camera can provide depth information in dynamic scenes, captured depth images are often noisy and of low resolution. In this paper, we propose an intensity-guided edge-preserving depth upsampling method through weighted L0 gradient minimization to enhance both resolution and visual quality of depth images. Guided by the high-resolution intensity image, we perform optimization to preserve boundaries of objects. We apply L0 gradient to the regularization term, and compute its weight from both intensity and depth images. We optimize the objective function using alternating minimization and half-quadratic splitting. Experimental results on Middlebury 2005, 2014, and real-world scene datasets demonstrate that the proposed method produces boundary-preserving depth upsampling results and outperforms state-of-the-art ones in terms of accuracy.

173