Semantic correspondence

69 papers with code • 5 benchmarks • 6 datasets

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

Patch-wise Graph Contrastive Learning for Image Translation

jcy132/PatchGCL 13 Dec 2023

Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input and output images.

3
13 Dec 2023

StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

rlawjdghek/stableviton 4 Dec 2023

Given a clothing image and a person image, an image-based virtual try-on aims to generate a customized image that appears natural and accurately reflects the characteristics of the clothing image.

552
04 Dec 2023

Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks

danaesavi/socialmedia-textimage-classification-auxlosses 14 Sep 2023

However, prior work on multimodal classification of social media posts has not yet addressed these challenges.

1
14 Sep 2023

AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks

kibeom-hong/aespa-net ICCV 2023

To deliver the artistic expression of the target style, recent studies exploit the attention mechanism owing to its ability to map the local patches of the style image to the corresponding patches of the content image.

28
19 Jul 2023

Instant Multi-View Head Capture through Learnable Registration

TimoBolkart/TEMPEH CVPR 2023

We use raw MVS scans as supervision during training, but, once trained, TEMPEH directly predicts 3D heads in dense correspondence without requiring scans.

106
12 Jun 2023

Emergent Correspondence from Image Diffusion

Tsingularity/dift NeurIPS 2023

We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images.

446
06 Jun 2023

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

Junyi42/sd-dino NeurIPS 2023

Text-to-image diffusion models have made significant advances in generating and editing high-quality images.

195
24 May 2023

Unsupervised Semantic Correspondence Using Stable Diffusion

ubc-vision/LDM_correspondences NeurIPS 2023

Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images.

37
24 May 2023

Going Denser with Open-Vocabulary Part Segmentation

cheems-seminar/grounded-segment-any-parts ICCV 2023

In this paper, we propose a detector with the ability to predict both open-vocabulary objects and their part segmentation.

355
18 May 2023

Temporal Consistent Automatic Video Colorization via Semantic Correspondence

bupt-ai-cz/tcvc 13 May 2023

Extensive experiments demonstrate that our method outperforms other methods in maintaining temporal consistency both qualitatively and quantitatively.

6
13 May 2023