2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 104 citations · 48 references
ComputingComputer ScienceComputer VisionFlow VisualizationMachine VisionMotion AnalysisMotion EstimationOptical FlowScene UnderstandingVideo AnalysisDeep Optical FlowFeature-based Optical FlowLearning-based Optical FlowMotion LearningMotion Representation LearningOptical Flow EstimationPrior Related KnowledgeSeparable Cost Structures
Full-motion cost volumes play a central role in current state-of-the-art optical flow methods. However, constructed using simple feature correlations, they lack the ability to encapsulate prior, or even non-local knowledge. This creates artifacts in poorly constrained ambiguous regions, such as occluded and textureless areas. We propose a separable cost volume module, a drop-in replacement to correlation cost volumes, that uses non-local aggregation layers to exploit global context cues and prior knowledge, in order to disambiguate motions in these regions. Our method leads both the now standard Sintel and KITTI optical flow benchmarks in terms of accuracy, and is also shown to generalize better from synthetic to real data.
48
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations
Vision meets robotics: The KITTI dataset
Andreas Geiger, Philip Lenz, Christoph Stiller et al. · The International Journal of Robotics Research · 2013 · 9.7K citations
FlowNet: Learning Optical Flow with Convolutional Networks
Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg et al. · 2015 · 4.2K citations