mlsanityData to 14 Oct 2026

From Keypoints to Realism: A Realistic and Accurate Virtual Try-on Network from 2D Images

arXiv 2504.03807 ↗First posted 4 Apr 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The aim of image-based virtual try-on is to generate realistic images of individuals wearing target garments, ensuring that the pose, body shape and characteristics of the target garment are accurately preserved. Existing methods often fail to reproduce the fine details of target garments effectively and lack generalizability to new scenarios. In the proposed method, the person's initial garment is completely removed. Subsequently, a precise warping is performed using the predicted keypoints to fully align the target garment with the body structure and pose of the individual. Based on the warped garment, a body segmentation map is more accurately predicted. Then, using an alignment-aware segment normalization, the misaligned areas between the warped garment and the predicted garment region in the segmentation map are removed. Finally, the generator produces the final image with high visual quality, reconstructing the precise characteristics of the target garment, including its overall shape and texture. This approach emphasizes preserving garment characteristics and improving adaptability to various poses, providing better generalization for diverse applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

21 of 33 references.

References · 21

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  4. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  6. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  7. 2016Least Squares Generative Adversarial Networkscited by 1,001
  8. 2018Self-Attention Generative Adversarial Networkscited by 809
  9. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  10. 2021VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalizationcited by 287
  11. 2017VITON: An Image-based Virtual Try-on Networkcited by 286
  12. 2018Toward Characteristic-Preserving Image-based Virtual Try-On Networkcited by 192
9 more
  1. 2022Dress Code: High-Resolution Multi-Category Virtual Try-Oncited by 162
  2. 2020Towards Photo-Realistic Virtual Try-On by Adaptively GeneratingleftrightarrowPreserving Image Contentcited by 149
  3. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  4. 2022C-VTON: Context-Driven Image-Based Virtual Try-On Networkcited by 29
  5. 2023Image-Based Virtual Try-On: A Surveycited by 19
  6. 2019VITON-GAN: Virtual Try-on Image Generator Trained with Adversarial Losscited by 14
  7. 2021Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)cited by 4
  8. 2021Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothingcited by 4
  9. 2022WG-VITON: Wearing-Guide Virtual Try-On for Top and Bottom Clothescited by 2

Built on by

Not cited yet.