HyperAIHyperAI
a month ago

Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features

Juhong Min; Jongmin Lee; Jean Ponce; Minsu Cho
Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features
Abstract

Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.

Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features | Latest Papers | HyperAI