MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

CVPR 2020 Shengyu ZhaoYilun ShengYue DongEric I-Chao ChangYan Xu

Feature warping is a core technique in optical flow estimation; however, the ambiguity caused by occluded areas during warping is a major problem that remains unsolved. In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Optical Flow Estimation KITTI 2012 MaskFlownet-S Average End-Point Error 1.1 # 1
Optical Flow Estimation KITTI 2012 MaskFlownet Average End-Point Error 1.1 # 1
Optical Flow Estimation KITTI 2015 MaskFlownet Fl-all 6.11 # 1
Optical Flow Estimation KITTI 2015 MaskFlownet-S Fl-all 6.81 # 2
Optical Flow Estimation Sintel-clean MaskFlownet-S Average End-Point Error 2.77 # 3
Optical Flow Estimation Sintel-clean MaskFlownet Average End-Point Error 2.52 # 1
Optical Flow Estimation Sintel-final MaskFlownet Average End-Point Error 4.17 # 2
Optical Flow Estimation Sintel-final MaskFlownet-S Average End-Point Error 4.38 # 4

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