EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow

Abstract

We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions. It consists of two steps: i) dense matching by edge-preserving interpolation from a sparse set of matches; ii) variational energy minimization initialized with the dense matches. The sparse-to-dense interpolation relies on an appropriate choice of the distance, namely an edge-aware geodesic distance. This distance is tailored to handle occlusions and motion boundaries -- two common and difficult issues for optical flow computation. We also propose an approximation scheme for the geodesic distance to allow fast computation without loss of performance. Subsequent to the dense interpolation step, standard one-level variational energy minimization is carried out on the dense matches to obtain the final flow estimation. The proposed approach, called Edge-Preserving Interpolation of Correspondences (EpicFlow) is fast and robust to large displacements. It significantly outperforms the state of the art on MPI-Sintel and performs on par on Kitti and Middlebury.

Cited by in corpus (18)

• FlowNet: Learning Optical Flow with Convolutional Networks
• Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
• Optical Flow Estimation using a Spatial Pyramid Network
• Learning Human Optical Flow
• Optical Flow with Semantic Segmentation and Localized Layers
• Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild
• Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
• ActionFlowNet: Learning Motion Representation for Action Recognition
• Improved Image Boundaries for Better Video Segmentation
• Unsupervised Learning of Edges
• Cascaded Scene Flow Prediction using Semantic Segmentation
• FusionNet and AugmentedFlowNet: Selective Proxy Ground Truth for Training on Unlabeled Images
• PatchBatch: a Batch Augmented Loss for Optical Flow
• A Continuous Optimization Approach for Efficient and Accurate Scene Flow
• Video-based Person Re-Identification using Gated Convolutional Recurrent Neural Networks
• Semantically Guided Depth Upsampling
• FALDOI: A new minimization strategy for large displacement variational optical flow
• Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation