correspondence problem

Deep Functional Maps: Structured Prediction for Dense Shape Correspondence

https://arxiv.org/abs/1704.08686

Learning Dense Correspondence via 3D-guided Cycle Consistency

https://people.eecs.berkeley.edu/~tinghuiz/papers/cvpr16_cycle.pdf

Generic 3D Representation via Pose Estimation and Matching

http://cvgl.stanford.edu/papers/zamir_eccv16.pdf
ProjectPage: http://3drepresentation.stanford.edu/

AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matching

https://arxiv.org/abs/1704.04749

comment

Pengsida: test

Self-Supervised Visual Descriptor Learning for Dense Correspondence

https://homes.cs.washington.edu/~tws10/3163.pdf

Universal Correspondence Network

http://cvgl.stanford.edu/projects/ucn/choy_nips16.pdf
ProjectPage: http://cvgl.stanford.edu/projects/ucn/