René Ranftl

Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation

In this work we present a novel method for the challenging problem of depth image up sampling. Modern depth cameras such as Kinect or Time-of-Flight cameras deliver dense, high quality depth measurements but are limited in their lateral resolution. To overcome this limitation we formulate a convex optimization problem using higher order regularization for depth image up sampling. In this optimization an an isotropic diffusion tensor, calculated from a high resolution intensity image, is used to guide the up sampling. We derive a numerical algorithm based on a primal-dual formulation that is efficiently parallelized and runs at multiple frames per second. We show that this novel up sampling clearly outperforms state of the art approaches in terms of speed and accuracy on the widely used Middlebury 2007 datasets. Furthermore, we introduce novel datasets with highly accurate ground truth, which, for the first time, enable to benchmark depth up sampling methods using real sensor data.

Pushing the limits of stereo using variational stereo estimation

We examine high accuracy stereo estimation for binocular sequences that where obtained from a mobile platform. The ultimate goal is to improve the range of stereo systems without altering the setup. Based on a well-known variational optical flow model, we introduce a novel stereo model that features a second-order regularization, which both allows sub-pixel accurate solutions and piecewise planar disparity maps. The model incorporates a robust fidelity term to account for adverse illumination conditions that frequently arise in real-world scenes. Using several sequences that were taken from a mobile platform we show the robustness and accuracy of the proposed model.

Non-local Total Generalized Variation for Optical Flow Estimation

In this paper we introduce a novel higher-order regularization term. The proposed regularizer is a non-local extension of the popular second-order Total Generalized variation, which favors piecewise affine solutions and allows to incorporate soft-segmentation cues into the regularization term. These properties make this regularizer especially appealing for optical flow estimation, where it offers accurately localized motion boundaries and allows to resolve ambiguities in the matching term. We additionally propose a novel matching term which is robust to illumination and scale changes, two major sources of errors in optical flow estimation algorithms. We extensively evaluate the proposed regularizer and data term on two challenging benchmarks, where we are able to obtain state of the art results. Our method is currently ranked first among classical two-frame optical flow methods on the KITTI optical flow benchmark.

Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs

This paper addresses a new learning algorithm for the recently introduced co-sparse analysis model. First, we give new insights into the co-sparse analysis model by establishing connections to filter-based MRF models, such as the field of experts model of Roth and Black. For training, we introduce a technique called bi-level optimization to learn the analysis operators. Compared with existing analysis operator learning approaches, our training procedure has the advantage that it is unconstrained with respect to the analysis operator. We investigate the effect of different aspects of the co-sparse analysis model and show that the sparsity promoting function (also called penalty function) is the most important factor in the model. In order to demonstrate the effectiveness of our training approach, we apply our trained models to various classical image restoration problems. Numerical experiments show that our trained models clearly outperform existing analysis operator learning approaches and are on par with state-of-the-art image denoising algorithms. Our approach develops a framework that is intuitive to understand and easy to implement.

Variational Shape from Light Field

In this paper we propose an efficient method to calculate a high-quality depth map from a single raw image captured by a light field or plenoptic camera. The proposed model combines the main idea of Active Wavefront Sampling AWS with the light field technique, i.e. we extract so-called sub-aperture images out of the raw image of a plenoptic camera, in such a way that the virtual view points are arranged on circles around a fixed center view. By tracking an imaged scene point over a sequence of sub-aperture images corresponding to a common circle, one can observe a virtual rotation of the scene point on the image plane. Our model is able to measure a dense field of these rotations, which are inversely related to the scene depth.

Revisiting Loss-Specific Training of Filter-Based MRFs for Image Restoration

It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision. Recent years have seen the emergence of two main approaches for learning the parameters in MRFs: (1) probabilistic learning using sampling-based algorithms and (2) loss-specific training based on MAP estimate. After investigating existing training approaches, it turns out that the performance of the loss-specific training has been significantly underestimated in existing work. In this paper, we revisit this approach and use techniques from bi-level optimization to solve it. We show that we can get a substantial gain in the final performance by solving the lower-level problem in the bi-level framework with high accuracy using our newly proposed algorithm. As a result, our trained model is on par with highly specialized image denoising algorithms and clearly outperforms probabilistically trained MRF models. Our findings suggest that for the loss-specific training scheme, solving the lower-level problem with higher accuracy is beneficial. Our trained model comes along with the additional advantage, that inference is extremely efficient. Our GPU-based implementation takes less than 1s to produce state-of-the-art performance.

Bilevel Optimization with Nonsmooth Lower Level Problems

We consider a bilevel optimization approach for parameter learning in nonsmooth variational models. Existing approaches solve this problem by applying implicit differentiation to a sufficiently smooth approximation of the nondifferentiable lower level problem. We propose an alternative method based on differentiating the iterations of a nonlinear primal–dual algorithm. Our method computes exact (sub)gradients and can be applied also in the nonsmooth setting. We show preliminary results for the case of multi-label image segmentation.

Dense Monocular Depth Estimation in Complex Dynamic Scenes

We present an approach to dense depth estimation from a single monocular camera that is moving through a dynamic scene. The approach produces a dense depth map from two consecutive frames. Moving objects are reconstructed along with the surrounding environment. We provide a novel motion segmentation algorithm that segments the optical flow field into a set of motion models, each with its own epipolar geometry. We then show that the scene can be reconstructed based on these motion models by optimizing a convex program. The optimization jointly reasons about the scales of different objects and assembles the scene in a common coordinate frame, determined up to a global scale. Experimental results demonstrate that the presented approach outperforms prior methods for monocular depth estimation in dynamic scenes.

Minimizing TGV-Based Variational Models with Non-convex Data Terms

We introduce a method to approximately minimize variational models with Total Generalized Variation regularization (TGV) and non-convex data terms. Our approach is based on a decomposition of the functional into two subproblems, which can be both solved globally optimal. Based on this decomposition we derive an iterative algorithm for the approximate minimization of the original non-convex problem. We apply the proposed algorithm to a state-of-the-art stereo model that was previously solved using coarse-to-fine warping, where we are able to show significant improvements in terms of accuracy.

A Deep Variational Model for Image Segmentation

In this paper we introduce a novel model that combines Deep Convolutional Neural Networks with a global inference model. Our model is derived from a convex variational relaxation of the minimum s-t cut problem on graphs, which is frequently used for the task of image segmentation. We treat the outputs of Convolutional Neural Networks as the unary and pairwise potentials of a graph and derive a smooth approximation to the minimum s-t cut problem. During training, this approximation facilitates the adaptation of the Convolutional Neural Network to the smoothing that is induced by the global model. The training algorithm can be understood as a modified backpropagation algorithm, that explicitly takes the global inference layer into account.