Depth Reconstruction from Sparse Samples: Representation, Algorithm, and Sampling
This work addresses depth reconstruction for 3D technology and computer vision applications, offering an incremental improvement over existing methods with limited performance.
The paper tackles the problem of recovering dense depth maps from sparse measurements by proposing a computationally efficient method that combines wavelet-contourlet dictionaries, an ADMM algorithm with multi-scale warm start, and a two-stage randomized sampling scheme, achieving high-quality dense depth estimates with robustness to noise.
The rapid development of 3D technology and computer vision applications have motivated a thrust of methodologies for depth acquisition and estimation. However, most existing hardware and software methods have limited performance due to poor depth precision, low resolution and high computational cost. In this paper, we present a computationally efficient method to recover dense depth maps from sparse measurements. We make three contributions. First, we provide empirical evidence that depth maps can be encoded much more sparsely than natural images by using common dictionaries such as wavelets and contourlets. We also show that a combined wavelet-contourlet dictionary achieves better performance than using either dictionary alone. Second, we propose an alternating direction method of multipliers (ADMM) to achieve fast reconstruction. A multi-scale warm start procedure is proposed to speed up the convergence. Third, we propose a two-stage randomized sampling scheme to optimally choose the sampling locations, thus maximizing the reconstruction performance for any given sampling budget. Experimental results show that the proposed method produces high quality dense depth estimates, and is robust to noisy measurements. Applications to real data in stereo matching are demonstrated.