Deep Discrete Flow

By Fatma Güney, Andreas Geiger. 2016

74 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials (2018, background): “In contrast, recent learning-based solutions to motion estimation [10, 15, 24], stereo matching [20, 21, 42] and 3D reconstruction [5, 6, 9, 16, 37] have demonstrated impressive results by learning feature representations that are much more robust to local viewpoint and lighting changes.”
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks (2016, neutral): “On the benchmark, in case of clean data this slightly degraded the result, while on final data FlowNet2–ft-sintel is on par with the currently published state-of-the art method DeepDiscreteFlow [13].”
Optical Flow Estimation Using a Spatial Pyramid Network (2016, methodology): “Deep matching methods [21, 32, 44] do not fully solve the problem, since they resort to classical methods to compute the final flow field.”
Video Frame Interpolation via Adaptive Separable Convolution (2017, methodology): “Our research is inspired by the success of applying deep learning to optical flow estimation [2, 12, 16, 19, 50, 51, 52], artistic style transfer [17, 22, 28], and image enhancement [6, 9, 10, 46, 47, 55, 57, 62, 65].”
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (2019, methodology): “Other than such end-to-end approaches, CNNs can also serve to extract learned feature descriptors, which are com bined with classical optimizers or well-designed correspon dence search methods to find matches between extracted features [4, 6, 16, 20, 59, 61].”
Conditional Affordance Learning for Driving in Urban Environments (2018, background): “, for object detection [8, 9], image segmentation [10, 11], depth [12, 13] or motion estimation [14, 15].”
Occlusion Aware Unsupervised Learning of Optical Flow (2017, methodology): “[21] uses deep nets to extract discriminative features to compute optical flow through patch matching.”
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems (2017, background): “optical flow [16] and stereo matching (disparity estimation) [46, 6, 27].”
SDC – Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks (2019, methodology): “Other architectures use dilated convolutions for context aggregation in an endto-end network after constructing coarse high-level features [13].”
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss (2017, methodology): “Motivated by the recent successes of end-to-end deep learning, convolutional neural networks (CNNs) have been suggested for addressing these challenges, and recently started to outperform many traditional flow methods in public benchmarks (Dosovitskiy et al. 2015; Gadot and Wolf 2016; Güney and Geig”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “In con- 10-2 10-1 100 101 102 Runtime (seconds per frame) 0 2 4 6 8 10 12 14 A v e ra g e E P E Yamaguchi (2013) Ilg (2016) Derome (2016) Güney & Geiger (2016) Weinzaepfel (2013) Revaud (2015) Timofte (2015) Bao (2014) Ranjan (2016) Wulff & Black (2015) Plyer (2014) Brox & Malik (2011) Zach…”
Video Frame Interpolation via Adaptive Convolution (2017, methodology): “Our work is inspired by the success of deep learning in solving not only difficult visual understanding problems [16, 20, 26, 28, 39, 40, 42, 45, 54, 60, 64] but also other computer vision problems like optical flow estimation [9, 14, 19, 48, 49, 52], style transfer [11, 15, 23, 30, 50], and image e”
AutoScaler: Scale-Attention Networks for Visual Correspondence (2016, methodology): “Our relative large EPE-unmatched number is due to the simplicity of our interpolation scheme using Epicflow compared to the time-consuming comprehensive MRF post-processing step to propagate the estimated flow to occluded regions as employed by many competing systems such as Flowfields [4], Discrete”