WLASL is the largest video dataset for Word-Level American Sign Language (ASL) recognition, which features 2,000 common different words in ASL. We hope WLASL will facilitate the research in sign language understanding and eventually benefit the communication between deaf and hearing communities.

The task of image-based virtual try-on aims to transfer a target clothing item onto the corresponding region of a person, which is commonly tackled by fitting the item to the desired body part and fusing the warped item with the person. While an increasing number of studies have been conducted, the resolution of synthesized images is still limited to low (e.g., 256x192), which acts as the critical limitation against satisfying online consumers. We argue that the limitation stems from several challenges: as the resolution increases, the artifacts in the misaligned areas between the warped clothes and the desired clothing regions become noticeable in the final results; the architectures used in existing methods have low performance in generating high-quality body parts and maintaining the texture sharpness of the clothes. To address the challenges, we propose a novel virtual try-on method called VITON-HD that successfully synthesizes 1024x768 virtual try-on images. Specifically, we first prepare the segmentation map to guide our virtual try-on synthesis, and then roughly fit the target clothing item to a given person's body. Next, we propose ALIgnment-Aware Segment (ALIAS) normalization and ALIAS generator to handle the misaligned areas and preserve the details of 1024x768 inputs. Through rigorous comparison with existing methods, we demonstrate that VITON-HD highly surpasses the baselines in terms of synthesized image quality both qualitatively and quantitatively.

Collection methodology: using software Processing with Python Mode. To generate a plane shapes like a hand-drawn, the Perlin Noise method is used (More info: https://github.com/reevald/FlatShapeNet). The dataset is used for the educational game Ariga.Currently the dataset (Version 4) is constructed by choosing 8 largest classes : "Circle", "Kite", "Parallelogram", "Square", "Rectangle", "Rhombus", "Trapezoid", and "Triangle". Each class contains 1,500 training samples, 500 validation samples, and 500 test samples. The total number of training samples is 12,000, validation samples 4,000, and testing 4,000. Each sample is an image measuring (224 x 224 x 3) (RGB).