SOTAVerified

Semantic correspondence

The task of semantic correspondence aims to establish reliable visual correspondence between different instances of the same object category.

Papers

Showing 2650 of 175 papers

TitleStatusHype
Convolutional Hough Matching NetworksCode1
Learning Implicit Functions for Topology-Varying Dense 3D Shape CorrespondenceCode1
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph ConvolutionCode1
Cost Aggregation Is All You Need for Few-Shot SegmentationCode1
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot SegmentationCode1
CoCosNet v2: Full-Resolution Correspondence Learning for Image TranslationCode1
Emergent Correspondence from Image DiffusionCode1
A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D FacesCode1
Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning NetworkCode1
CATs++: Boosting Cost Aggregation with Convolutions and TransformersCode1
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression SegmentationCode1
Attentive Normalization for Conditional Image GenerationCode1
Deep ViT Features as Dense Visual DescriptorsCode1
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete LabelsCode1
Learning to Compose Hypercolumns for Visual CorrespondenceCode1
Color2Embed: Fast Exemplar-Based Image Colorization using Color EmbeddingsCode1
Multi-Compound Transformer for Accurate Biomedical Image SegmentationCode1
Multi-scale Matching Networks for Semantic CorrespondenceCode1
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionCode1
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence LearningCode1
Patch-wise Graph Contrastive Learning for Image TranslationCode1
AesPA-Net: Aesthetic Pattern-Aware Style Transfer NetworksCode1
Doubly Deformable Aggregation of Covariance Matrices for Few-shot SegmentationCode1
Semantic Correspondence as an Optimal Transport ProblemCode1
Learning Semantic Correspondence with Sparse AnnotationsCode1
Show:102550
← PrevPage 2 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GeoAware-SC (Supervised, AP-10K P.T.)PCK85.6Unverified
2DINOv2PCK85.2Unverified
3GeoAware-SC (Supervised)PCK82.9Unverified
4SD+DINO (Supervised)PCK74.6Unverified
5GeoAware-SC + CleanDIFT (Zero-Shot)PCK70Unverified
6GeoAware-SC (Zero-Shot)PCK68.5Unverified
7SD+DINO + CleanDIFT (Zero-Shot)PCK64.8Unverified
8IFCATPCK64.4Unverified
9SD+DINO (Zero-shot)PCK64Unverified
10DIFT + CleanDIFT (Zero-Shot)PCK61.4Unverified
#ModelMetricClaimedVerifiedStatus
1DINOv2PCK95.8Unverified
2GeoAware-SC (Supervised, AP-10K P.T.)PCK95.7Unverified
3GeoAware-SC (Supervised)PCK95.1Unverified
4CATs++PCK93.8Unverified
5SD+DINO (Supervised)PCK93.6Unverified
6CATsPCK92.6Unverified
7VAT (ECCV)PCK92.3Unverified
8VATPCK92.3Unverified
9CHMPCK91.6Unverified
10DHPFPCK90.7Unverified
#ModelMetricClaimedVerifiedStatus
1LDMCorrespondencesPCK84.3Unverified
2VAT (ECCV)PCK81.6Unverified
3VATPCK81Unverified
4CHMPCK79.4Unverified
5CATsPCK79.2Unverified
6SCOTPCK78.1Unverified
7DHPFPCK77.6Unverified
8HPFPCK76.3Unverified
#ModelMetricClaimedVerifiedStatus
1HPFIoU63Unverified
2DHPFIoU62Unverified
#ModelMetricClaimedVerifiedStatus
1DINOv2PCK87.4Unverified
#ModelMetricClaimedVerifiedStatus
1LDM CorrespondencesMean PCK@0.0561.6Unverified