Attribute editing has become an important and emerging topic of computer vision. In this paper, we consider a task: given a reference garment image A and another image B with target attribute (collar/sleeve), generate a photo-realistic image which combines the texture from reference A and the new attribute from reference B. The highly convoluted attributes and the lack of paired data are the main challenges to the task. To overcome those limitations, we propose a novel self-supervised model to synthesize garment images with disentangled attributes (e.g., collar and sleeves) without paired data. Our method consists of a reconstruction learning step and an adversarial learning step. The model learns texture and location information through reconstruction learning. And, the model's capability is generalized to achieve single-attribute manipulation by adversarial learning. Meanwhile, we compose a new dataset, named GarmentSet, with annotation of landmarks of collars and sleeves on clean garment images. Extensive experiments on this dataset and real-world samples demonstrate that our method can synthesize much better results than the state-of-the-art methods in both quantitative and qualitative comparisons.
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）
Visual fashion analysis has attracted many attentions in the recent years. Previous work represented clothing regions by either bounding boxes or human joints. This work presents fashion landmark detection or fashion alignment, which is to predict the positions of functional key points defined on the fashion items, such as the corners of neckline, hemline, and cuff. To encourage future studies, we introduce a fashion landmark dataset with over 120K images, where each image is labeled with eight landmarks. With this dataset, we study fashion alignment by cascading multiple convolutional neural …
What defines a visual style? Fashion styles emerge organically from how people assemble outfits of clothing, making them difficult to pin down with a computational model. Low-level visual similarity can be too specific to detect stylistically similar images, while manually crafted style categories can be too abstract to capture subtle style differences. We propose an unsupervised approach to learn a style-coherent representation. Our method leverages probabilistic polylingual topic models based on visual attributes to discover a set of latent style factors. Given a collection of unlabeled fash…
UT Austin（德克萨斯大学奥斯汀分校）；Facebook AI Research（Facebook人工智能研究）；Georgia Tech（佐治亚理工学院）；Cornell Tech（康奈尔科技学院）
Given an outfit, what small changes would most improve its fashionability? This question presents an intriguing new vision challenge. We introduce Fashion++, an approach that proposes minimal adjustments to a full-body clothing outfit that will have maximal impact on its fashionability. Our model consists of a deep image generation neural network that learns to synthesize clothing conditioned on learned per-garment encodings. The latent encodings are explicitly factorized according to shape and texture, thereby allowing direct edits for both fit/presentation and color/patterns/material, respec…
Fashion is an increasingly important topic in computer vision, in particular the so-called street-to-shop task of matching street images with shop images containing similar fashion items. Solving this problem promises new means of making fashion searchable and helping shoppers find the articles they are looking for. This paper focuses on finding pieces of clothing worn by a person in full-body or half-body images with neutral backgrounds. Such images are ubiquitous on the web and in fashion blogs, and are typically studio photos, we refer to this setting as studio-to-shop. Recent advances in c…
Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；Farfetch
A picture is worth a thousand words. Albeit a cliché, for the fashion industry, an image of a clothing piece allows one to perceive its category (e.g., dress), sub-category (e.g., day dress) and properties (e.g., white colour with floral patterns). The seasonal nature of the fashion industry creates a highly dynamic and creative domain with evermore data, making it unpractical to manually describe a large set of images (of products). In this paper, we explore the concept of visual recognition for fashion images through an end-to-end architecture embedding the hierarchical nature of the annotat…
North Carolina State University（北卡罗来纳州立大学）；JD.com American Technologies（京东美国技术公司）；OPPO US Research Center（OPPO美国研究中心）
Generating a photorealistic image with intended human pose is a promising yet challenging research topic for many applications such as smart photo editing, movie making, virtual try-on, and fashion display. In this paper, we present a novel deep generative model to transfer an image of a person from a given pose to a new pose while keeping fashion item consistent. In order to formulate the framework, we employ one generator and two discriminators for image synthesis. The generator includes an image encoder, a pose encoder and a decoder. The two encoders provide good representation of visual an…
Shenzhen Campus of Sun Yat-Sen University（中山大学深圳校区）；UiT The Arctic University of Norway（挪威北极大学）；ByteDance（字节跳动）；Meituan Inc.（美团公司）；Shidi Inc.（石迪公司）
Cross-modal fashion image synthesis has emerged as one of the most promising directions in the generation domain due to the vast untapped potential of incorporating multiple modalities and the wide range of fashion image applications. To facilitate accurate generation, cross-modal synthesis methods typically rely on Contrastive Language-Image Pre-training (CLIP) to align textual and garment information. In this work, we argue that simply aligning texture and garment information is not sufficient to capture the semantics of the visual information and therefore propose MaskCLIP. MaskCLIP decompo…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Group Limited（商汤集团有限公司）
Fashion landmarks are functional key points defined on clothes, such as corners of neckline, hemline, and cuff. They have been recently introduced as an effective visual representation for fashion image understanding. However, detecting fashion landmarks are challenging due to background clutters, human poses, and scales. To remove the above variations, previous works usually assumed bounding boxes of clothes are provided in training and test as additional annotations, which are expensive to obtain and inapplicable in practice. This work addresses unconstrained fashion landmark detection, wher…
For fashion outfits to be considered aesthetically pleasing, the garments that constitute them need to be compatible in terms of visual aspects, such as style, category and color. Previous works have defined visual compatibility as a binary classification task with items in a garment being considered as fully compatible or fully incompatible. However, this is not applicable to Outfit Maker applications where users create their own outfits and need to know which specific items may be incompatible with the rest of the outfit. To address this, we propose the Visual InCompatibility TransfORmer (VI…
IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；NExT++ Research Centre, National University of Singapore（新加坡国立大学NExT++研究中心）；College of Information Science and Technology and Artificial Intelligence, Nanjing Forestry University（南京林业大学信息科学与技术学院及人工智能学院）
UC San Diego（加州大学圣地亚哥分校）；Pinterest；Stanford University（斯坦福大学）
Modeling fashion compatibility is challenging due to its complexity and subjectivity. Existing work focuses on predicting compatibility between product images (e.g. an image containing a t-shirt and an image containing a pair of jeans). However, these approaches ignore real-world 'scene' images (e.g. selfies); such images are hard to deal with due to their complexity, clutter, variations in lighting and pose (etc.) but on the other hand could potentially provide key context (e.g. the user's body type, or the season) for making more accurate recommendations. In this work, we propose a new task …
