Search Results for author: Kedan Li

Found 6 papers, 0 papers with code

Preserving Image Properties Through Initializations in Diffusion Models

no code implementations4 Jan 2024 Jeffrey Zhang, Shao-Yu Chang, Kedan Li, David Forsyth

The usual practice of training the denoiser with a very noisy image and starting inference with a sample of pure noise leads to inconsistent generated images during inference.

Wearing the Same Outfit in Different Ways -- A Controllable Virtual Try-on Method

no code implementations29 Nov 2022 Kedan Li, Jeffrey Zhang, Shao-Yu Chang, David Forsyth

However, no current method can both control how the garment is worn -- including tuck or untuck, opened or closed, high or low on the waist, etc.. -- and generate realistic images that accurately preserve the properties of the original garment.

Virtual Try-on

Toward Accurate and Realistic Outfits Visualization with Attention to Details

no code implementations CVPR 2021 Kedan Li, Min Jin Chong, Jeffrey Zhang, Jingen Liu

Prior works produce images that are filled with artifacts and fail to capture important visual details necessary for commercial applications.

Image Generation Virtual Try-on

Toward Accurate and Realistic Virtual Try-on Through Shape Matching and Multiple Warps

no code implementations22 Mar 2020 Kedan Li, Min Jin Chong, Jingen Liu, David Forsyth

However, obtaining a realistic image is challenging because the kinematics of garments is complex and because outline, texture, and shading cues in the image reveal errors to human viewers.

Image Generation Virtual Try-on

Coherent and Controllable Outfit Generation

no code implementations17 Jun 2019 Kedan Li, Chen Liu, David Forsyth

A user study suggests that people understand the match between the queries and the outfits produced by our method.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.