Semantic correspondence
70 papers with code • 5 benchmarks • 7 datasets
The task of semantic correspondence aims to establish reliable visual correspondence between different instances of the same object category.
Benchmarks
These leaderboards are used to track progress in Semantic correspondence
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
CUB-200-2011
Caltech-101
SPair-71k
PF-PASCAL
PF-WILLOW
FunKPoint
AVMIT
Most implemented papers
A Robust Multilinear Model Learning Framework for 3D Faces
Multilinear models are widely used to represent the statistical variations of 3D human faces as they decouple shape changes due to identity and expression.
FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence
The sampling patterns of local structure and the self-similarity measure are jointly learned within the proposed network in an end-to-end and multi-scale manner.
SCNet: Learning Semantic Correspondence
This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category.
Recurrent Transformer Networks for Semantic Correspondence
Our networks accomplish this through an iterative process of estimating spatial transformations between the input images and using these transformations to generate aligned convolutional activations.
Deep Exemplar-based Video Colorization
zhangmozhe/video-colorization
•
•
CVPR 2019
This paper presents the first end-to-end network for exemplar-based video colorization.
Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features
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.
Dynamic Context Correspondence Network for Semantic Alignment
ShuaiyiHuang/DCCNet
•
•
ICCV 2019
We instantiate our strategy by designing an end-to-end learnable deep network, named as Dynamic Context Correspondence Network (DCCNet).
CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly.
Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence
thunlp/scorp
•
•
We find that sememes of each word are usually semantically matched to different words in its dictionary definition, and we name this matching relationship local semantic correspondence.
Correspondence Networks with Adaptive Neighbourhood Consensus
ActiveVisionLab/ANCNet
•
•
CVPR 2020
This is a challenging task due to large intra-class variations and a lack of dense pixel level annotations.
