Compatible and Diverse Fashion Image Inpainting

Han, Xintong; Wu, Zuxuan; Huang, Weilin; Scott, Matthew R.; Davis, Larry S.

doi:10.48550/arxiv.1902.01096

Cited by 3 publications

(6 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, Liu et al [56] proposed a GAN-based method for image inpainting on face images. FiNet [57] is another approach found in literature for fashion image inpainting that consists of completing the missing parts in fashion images.…”

Section: Gan-based Approachesmentioning

confidence: 99%

Image Inpainting: A Review

Elharrouss

Almaadeed

Al‐Maadeed

et al. 2019

Neural Process Lett

271

100

View full text Add to dashboard Cite

Although image inpainting, or the art of repairing the old and deteriorated images, has been around for many years, it has gained even more popularity because of the recent development in image processing techniques. With the improvement of image processing tools and the flexibility of digital image editing, automatic image inpainting has found important applications in computer vision and has also become an important and challenging topic of research in image processing. This paper is a brief review of the existing image inpainting approaches we first present a global vision on the existing methods for image inpainting. We attempt to collect most of the existing approaches and classify them into three categories, namely, sequential-based, CNN-based and GAN-based methods. In addition, for each category, a list of methods for the different types of distortion on the images is presented. Furthermore, collect a list of the available datasets and discuss these in our paper. This is a contribution for digital image inpainting researchers trying to look for the available datasets because there is a lack of datasets available for image inpainting. As the final step in this overview, we present the results of real evaluations of the three categories of image inpainting methods performed on the datasets used, for the different types of image distortion. In the end, we also present the evaluations metrics and discuss the performance of these methods in terms of these metrics. This overview can be used as a reference for image inpainting researchers, and it can also facilitate the comparison of the methods as well as the datasets used. The main contribution of this paper is the presentation of the three categories of image inpainting methods along with a list of available datasets that the researchers can use to evaluate their proposed methodology against.

show abstract

Section: Gan-based Approachesmentioning

confidence: 99%

Image Inpainting: A Review

Elharrouss

Almaadeed

Al‐Maadeed

et al. 2019

Neural Process Lett

271

100

View full text Add to dashboard Cite

show abstract

“…The procedure is continuous until the discriminator is unable to judge whether the output result of the generator is true or not. By taking advantage of the GAN, researchers make great progress in image-to-image translation [23], [55], [37], photo inpainting [15], clothing translation [53], [41], etc. Extensive learning tasks verify the effectiveness of image synthesis.…”

Section: Related Workmentioning

confidence: 99%

“…These methods have adopted the concept of GAN [12] and focus on generating the synthetic and realistic try-on images by preserving the characteristics of a clothing image (e.g., texture, logo, and embroidery) as well as warping it to an arbitrary human pose. Typical methods for virtual try-on include VITON [17], CP-VTON [47], VTNFP [52], ACGPN [51], et al [39], [38], [42], [41], [37], [13], [56], [15]. Extensive simulation results show the effectiveness of the proposed work.…”

Section: Introductionmentioning

confidence: 98%

Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing

Liu¹,

Zhao²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning based virtual try-on system has achieved some encouraging progress recently, but there still remain several big challenges that need to be solved, such as trying on arbitrary clothes of all types, trying on the clothes from one category to another and generating image-realistic results with few artifacts. To handle this issue, we in this paper first collect a new dataset with all types of clothes, i.e. tops, bottoms, and whole clothes, each one has multiple categories with rich information of clothing characteristics such as patterns, logos, and other details. Based on this dataset, we then propose the Arbitrary Virtual Try-On Network (AVTON) that is utilized for all-type clothes, which can synthesize realistic try-on images by preserving and trading off characteristics of the target clothes and the reference person. Our approach includes three modules: 1) Limbs Prediction Module, which is utilized for predicting the human body parts by preserving the characteristics of the reference person. This is especially good for handling crosscategory try-on task (e.g. long sleeves ↔ short sleeves or long pants ↔ skirts, etc.), where the exposed arms or legs with the skin colors and details can be reasonably predicted; 2) Improved Geometric Matching Module, which is designed to warp clothes according to the geometry of the target person. We improve the TPS based warping method with a compactly supported radial function (Wendland's Ψ-function); 3) Trade-Off Fusion Module, which is to trade off the characteristics of the warped clothes and the reference person. This module is to make the generated try-on images look more natural and realistic based on a finetune symmetry of the network structure. Extensive simulations are conducted and our approach can achieve better performance compared with the state-of-the-art virtual try-on methods.

show abstract

“…Fortunately, while human bodies can make a variety of postures and actions, they still have a roughly fixed form and topology, allowing the utilization of prior information such as segmentation maps (Wu et al 2019;Zhao et al 2021b;Han et al 2019) and posture (Lassner, Pons-Moll, and Gehler 2017;Balakrishnan et al 2018;Men et al 2020;Grigorev et al 2019). Most previous approaches for human image inpainting first complete a partially occluded human parsing map and then use it as a prior to guide the completion of the images.…”

Section: Introductionmentioning

confidence: 99%

“…The cooperative completion strategy enables the network to better learn and understand the relationship between people and the environment in the image with the help of the segmenta-Figure 3: Illustration of prior guided completion process. (a) Classical prior guided methods such as (Wu et al 2019;Zhao et al 2021b;Han et al 2019) usually complete the prior information first, and then complete the image. (b) Our proposed LOHC completes both prior and image simultaneously, enabling a bidirectional interaction between the prior and image information.…”

Section: Introductionmentioning

confidence: 99%

Large Occluded Human Image Completion via Image-Prior Cooperating

Zhao,

Zeng,

et al. 2024

AAAI

View full text Add to dashboard Cite

The completion of large occluded human body images poses a unique challenge for general image completion methods. The complex shape variations of human bodies make it difficult to establish a consistent understanding of their structures. Furthermore, as human vision is highly sensitive to human bodies, even slight artifacts can significantly compromise image fidelity. To address these challenges, we propose a large occluded human image completion (LOHC) model based on a novel image-prior cooperative completion strategy. Our model leverages human segmentation maps as a prior, and completes the image and prior simultaneously. Compared to the widely adopted prior-then-image completion strategy for object completion, this cooperative completion process fosters more effective interaction between the prior and image information. Our model consists of two stages. The first stage is a transformer-based auto-regressive network that predicts the overall structure of the missing area by generating a coarse completed image at a lower resolution. The second stage is a convolutional network that refines the coarse images. As the coarse result may not always be accurate, we propose a Dynamic Fusion Module (DFM) to selectively fuses the useful features from the coarse image with the original input at spatial and channel levels. Through extensive experiments, we demonstrate our method’s superior performance compared to state-of-the-art methods.

show abstract

Compatible and Diverse Fashion Image Inpainting

Cited by 3 publications

References 58 publications

Image Inpainting: A Review

Image Inpainting: A Review

Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing

Large Occluded Human Image Completion via Image-Prior Cooperating

Contact Info

Product

Resources

About