Semantic Attribute Matching Networks
This addresses the challenge of semantic image manipulation and matching for computer vision applications, representing an incremental hybrid approach.
The paper tackles the joint problem of establishing correspondences and transferring attributes across semantically similar images, achieving state-of-the-art performance on multiple benchmarks.
We present semantic attribute matching networks (SAM-Net) for jointly establishing correspondences and transferring attributes across semantically similar images, which intelligently weaves the advantages of the two tasks while overcoming their limitations. SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences. To learn the networks using weak supervisions in the form of image pairs, we present a semantic attribute matching loss based on the matching similarity between an attribute transferred source feature and a warped target feature. With SAM-Net, the state-of-the-art performance is attained on several benchmarks for semantic matching and attribute transfer.