ScopeFlow: Dynamic Scene Scoping for Optical Flow

CVPR 2020 Aviram Bar-HaimLior Wolf

We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling challenging data that exists in the current training protocol, and improving the sampling process... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Optical Flow Estimation Sintel-clean ScopeFlow Average End-Point Error 3.592 # 6
Optical Flow Estimation Sintel-final ScopeFlow Average End-Point Error 4.098 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet