Image-Guided Depth Upsampling via Hessian and TV Priors

We propose a method that combines sparse depth (LiDAR) measurements with an intensity image and to produce a dense high-resolution depth image. As there are few, but accurate, depth measurements from the scene, our method infers the remaining depth values by incorporating information from the intensity image, namely the magnitudes and directions of the identified edges, and by assuming that the scene is composed mostly of flat surfaces. Such inference is achieved by solving a convex optimisation problem with properly weighted regularisers that are based on the `1-norm (specifically, on total variation). We solve the resulting problem with a computationally efficient ADMM-based algorithm. Using the SYNTHIA and KITTI datasets, our experiments show that the proposed method achieves a depth reconstruction performance comparable to or better than other model-based methods.

[1]  Michael Felsberg,et al.  Confidence Propagation through CNNs for Guided Sparse Depth Regression , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jean Ponce,et al.  Robust Guided Image Filtering Using Nonconvex Potentials , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Horst Bischof,et al.  Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation , 2013, 2013 IEEE International Conference on Computer Vision.

[4]  Miguel R. D. Rodrigues,et al.  Multimodal Image Super-Resolution via Joint Sparse Representations Induced by Coupled Dictionaries , 2017, IEEE Transactions on Computational Imaging.

[5]  Marc Pollefeys,et al.  Semantically Guided Depth Upsampling , 2016, GCPR.

[6]  Jonathan T. Barron,et al.  The Fast Bilateral Solver , 2015, ECCV.

[7]  Klaus Diepold,et al.  Dense disparity maps from sparse disparity measurements , 2011, 2011 International Conference on Computer Vision.

[8]  S. Setzer,et al.  Infimal convolution regularizations with discrete ℓ1-type functionals , 2011 .

[9]  Xiaoou Tang,et al.  Depth Map Super-Resolution by Deep Multi-Scale Guidance , 2016, ECCV.

[10]  Evaggelia Tsiligianni,et al.  A framework for learning affine transformations for multimodal sparse reconstruction , 2017, Optical Engineering + Applications.

[11]  Truong Q. Nguyen,et al.  Depth Reconstruction From Sparse Samples: Representation, Algorithm, and Sampling , 2014, IEEE Transactions on Image Processing.

[12]  Antonio M. López,et al.  The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Yonina C. Eldar,et al.  Compressed sensing for longitudinal MRI: An adaptive-weighted approach. , 2014, Medical physics.

[14]  Thomas Brox,et al.  Sparsity Invariant CNNs , 2017, 2017 International Conference on 3D Vision (3DV).

[15]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[16]  Miguel R. D. Rodrigues,et al.  Compressed Sensing With Prior Information: Strategies, Geometry, and Bounds , 2017, IEEE Transactions on Information Theory.

[17]  Jian Sun,et al.  Guided Image Filtering , 2010, ECCV.

[18]  Ming-Yu Liu,et al.  Joint Geodesic Upsampling of Depth Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.