Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation

By David Ferstl, Christian Reinbacher, René Ranftl, Matthias Rüther, Horst Bischof. IEEE International Conference on Computer Vision, 2013

526 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/baddafc5c72945685d4d69d7e3371f9584e22733

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Depth with Convolutional Spatial Propagation Network (2018, background): “Traditionally, depth output can be also efficiently enhanced with explicitly designed affinity through image filtering [24], [57], or data-driven ones through total variation (TV) [58], [59] and learning to dif-”
The Fast Bilateral Solver (2015, methodology): “Optimization algorithms of this nature have been used in global stereo [30], semantic segmentation [7, 20, 25, 38], depth superresolution [8, 17, 22, 24, 26, 27], and colorization [23].”
Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network (2018, background): “Traditionally, depth output can be also efficiently enhanced with explicitly designed affinity through image filtering [28,29], or data-driven ones through total variation (TV) [30,31] and learning to diffuse [32] by incorporating more priors into diffusion partial differential equations (PDEs).”
Deep Joint Image Filtering (2016, methodology): “Among them, JBU [4], GF [6] and Ham [13] are generic methods for joint image upsampling while MRF [16], TGV [3] and Park [2] are algorithms specifically designed for image guided depth upsampling.”
DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image (2018, methodology): “Non-learning based approaches [44, 2, 12] do not perform well possibly because of drastic illumination change and complicate scene structures.”
Depth Map Super-Resolution by Deep Multi-Scale Guidance (2016, methodology): “Figure S2 shows the convergence curves using f2 ∈ (3, 9, 11).”
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (2019, background): “A plethora of acceleration approaches have been proposed toward achieving real-time performance, such as solution space pruning [6], coarse-to-fine cost volume computation [16] and efficient variational optimization [10].”
Learning Guided Convolutional Network for Depth Completion (2019, background): “…information, edge information, or surface information, etc. Earlier works mainly address depth super-resolution with bilateral ﬁltering [16], or global energy minimization [26]–[28], where the depth completion is guided by image [16], [26]–[28], semantic segmentation [29] or edge information [30].”
Deep Depth Completion of a Single RGB-D Image (2018, methodology): “As such, the methods we consider include: a) joint bilinear ﬁltering [64] (Bilateral), b) fast bilateral solver [5] (Fast), and c) global edge-aware energy optimization [20] (TGV).”
ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data (2021, methodology): “Initial classical approaches to color-guided depth upsampling include both optimization and filtering-based methods [38, 39].”
Color-Guided Depth Recovery From RGB-D Data Using an Adaptive Autoregressive Model (2014, methodology): “Upsampling results (Table I) on Art , Book , and Moebius for MRF, JBFcv, Guided, Edge, and TGV are quoted from [11] and [34].”
Sparsity Invariant CNNs (2017, methodology): “Note that in contrast to other techniques [12, 52] which artiﬁcially upsample the input (e.g., via interpolation), our approach operates directly on the input and doesn’t introduce additional distractors.”