Darks and Stripes: Effects of Clothing on Weight Perception
- URL: http://arxiv.org/abs/2012.14274v1
- Date: Fri, 11 Dec 2020 16:14:40 GMT
- Title: Darks and Stripes: Effects of Clothing on Weight Perception
- Authors: Kirill Martynov, Kiran Garimella, Robert West
- Abstract summary: Two anecdotal rules, widespread in the world of fashion, are (1) choose dark clothes and (2) avoid horizontal stripes, in order to appear slim.
We present the results from a series of large-scale crowdsourcing studies that investigate the above two claims.
- Score: 16.045413159119317
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In many societies, appearing slim is considered attractive. The fashion
industry has been attempting to cater to this trend by designing outfits that
can enhance the appearance of slimness. Two anecdotal rules, widespread in the
world of fashion, are (1) choose dark clothes and (2) avoid horizontal stripes,
in order to appear slim. Thus far, empirical evidence has been unable to
conclusively determine the validity of these rules, and there is consequently
much controversy regarding the impact of both color and patterns on the visual
perception of weight. In this paper, we aim to close this gap by presenting the
results from a series of large-scale crowdsourcing studies that investigate the
above two claims. We gathered a dataset of around 1,000 images of people from
the Web together with their ground-truth weight and height, as well as clothing
attributes about colors and patterns. To elicit the effects of colors and
patterns, we asked crowd workers to estimate the weight in each image. For the
analysis, we controlled potential confounds by matching images in pairs where
the two images differ with respect to color or pattern, but are similar with
respect to other relevant aspects. We created image pairs in two ways: first,
observationally, i.e., from two real images; and second, experimentally, by
manipulating the color or pattern of clothing in a real image via photo
editing. Based on our analysis, we conclude that (1) dark clothes indeed
decrease perceived weight slightly but statistically significantly, and (2)
horizontal stripes have no discernible effect compared to solid light-colored
clothes. These results contribute to advancing the debate around the effect of
specific clothing colors and patterns and thus provide empirical grounds for
everyday fashion decisions. Moreover, our work gives an outlook on the vast
opportunities of using crowd sourcing in the modern fashion industry.
Related papers
- TryOnDiffusion: A Tale of Two UNets [46.54704157349114]
Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person.
A key challenge is to synthesize a detail-preserving visualization of the garment, while warping the garment to accommodate a significant body pose and shape change.
We propose a diffusion-based architecture that unifies two UNets (referred to as Parallel-UNet)
arXiv Detail & Related papers (2023-06-14T06:25:58Z) - Learning Fashion Compatibility from In-the-wild Images [6.591937706757015]
We propose to learn representations for compatibility prediction from in-the-wild street fashion images through self-supervised learning.
Our pretext task is formulated such that the representations of different items worn by the same person are closer compared to those worn by other people.
We conduct experiments on two popular fashion compatibility benchmarks - Polyvore and Polyvore-Disjoint outfits.
arXiv Detail & Related papers (2022-06-13T09:05:25Z) - Dress Code: High-Resolution Multi-Category Virtual Try-On [30.166151802234555]
Dress Code is more than 3x larger than publicly available datasets for image-based virtual try-on.
We leverage a semantic-aware discriminator that makes predictions at pixel-level instead of image- or patch-level.
arXiv Detail & Related papers (2022-04-18T19:31:49Z) - From Culture to Clothing: Discovering the World Events Behind A Century
of Fashion Images [100.20851232528925]
We propose a data-driven approach to identify specific cultural factors affecting the clothes people wear.
Our work is a first step towards a computational, scalable, and easily refreshable approach to link culture to clothing.
arXiv Detail & Related papers (2021-02-02T18:58:21Z) - Modeling Fashion Influence from Photos [108.58097776743331]
We explore fashion influence along two channels: geolocation and fashion brands.
We leverage public large-scale datasets of 7.7M Instagram photos from 44 major world cities.
Our results indicate the advantage of grounding visual style evolution both spatially and temporally.
arXiv Detail & Related papers (2020-11-17T20:24:03Z) - Apparel-invariant Feature Learning for Apparel-changed Person
Re-identification [70.16040194572406]
Most public ReID datasets are collected in a short time window in which persons' appearance rarely changes.
In real-world applications such as in a shopping mall, the same person's clothing may change, and different persons may wearing similar clothes.
It is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes.
arXiv Detail & Related papers (2020-08-14T03:49:14Z) - Unsupervised Landmark Learning from Unpaired Data [117.81440795184587]
Recent attempts for unsupervised landmark learning leverage synthesized image pairs that are similar in appearance but different in poses.
We propose a cross-image cycle consistency framework which applies the swapping-reconstruction strategy twice to obtain the final supervision.
Our proposed framework is shown to outperform strong baselines by a large margin.
arXiv Detail & Related papers (2020-06-29T13:57:20Z) - Person Re-identification by Contour Sketch under Moderate Clothing
Change [95.83034113646657]
Person re-id, the process of matching pedestrian images across different camera views, is an important task in visual surveillance.
In this work, we call the person re-id under clothing change the "cross-clothes person re-id"
Due to the lack of a large-scale dataset for cross-clothes person re-id, we contribute a new dataset that consists of 33698 images from 221 identities.
arXiv Detail & Related papers (2020-02-06T15:13:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.