Feature Matching

MaskFlownet is 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. The learned occlusion mask can be further fed into a subsequent network cascade with dual feature pyramids.

Source: MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Optical Flow Estimation 1 100.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories