SOTAVerified

Semantic correspondence

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

Papers

Showing 125 of 175 papers

TitleStatusHype
Zero-shot Image Editing with Reference ImitationCode5
StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-OnCode3
Semantic Gesticulator: Semantics-Aware Co-Speech Gesture SynthesisCode3
CleanDIFT: Diffusion Features without NoiseCode2
Going Denser with Open-Vocabulary Part SegmentationCode2
Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion ModelsCode2
A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic CorrespondenceCode2
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionCode1
CoCosNet v2: Full-Resolution Correspondence Learning for Image TranslationCode1
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression SegmentationCode1
Doubly Deformable Aggregation of Covariance Matrices for Few-shot SegmentationCode1
Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning NetworkCode1
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete LabelsCode1
Cost Aggregation Is All You Need for Few-Shot SegmentationCode1
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph ConvolutionCode1
Attentive Normalization for Conditional Image GenerationCode1
CATs++: Boosting Cost Aggregation with Convolutions and TransformersCode1
Convolutional Hough Matching NetworksCode1
Cora: Correspondence-aware image editing using few step diffusionCode1
Color2Embed: Fast Exemplar-Based Image Colorization using Color EmbeddingsCode1
Correspondence Networks with Adaptive Neighbourhood ConsensusCode1
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence LearningCode1
AesPA-Net: Aesthetic Pattern-Aware Style Transfer NetworksCode1
Deep ViT Features as Dense Visual DescriptorsCode1
A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D FacesCode1
Show:102550
← PrevPage 1 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
7VATPCK92.3Unverified
8VAT (ECCV)PCK92.3Unverified
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