FastCLIPstyler: Optimisation-free Text-based Image Style Transfer Using Style Representations

no code implementations • 7 Oct 2022 • Ananda Padhmanabhan Suresh, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Ukrit Watchareeruetai, Aubin Samacoits

In recent years, language-driven artistic style transfer has emerged as a new type of style transfer technique, eliminating the need for a reference style image by using natural language descriptions of the style.

Style Transfer

Amortized Variational Inference: A Systematic Review

no code implementations • 22 Sep 2022 • Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetai

The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem.

Representation Learning Variational Inference

LOTR: Face Landmark Localization Using Localization Transformer

no code implementations • 21 Sep 2021 • Ukrit Watchareeruetai, Benjaphan Sommana, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Aubin Samacoits, Samuel W. F. Earp, Nakarin Sritrakool

The proposed framework is a direct coordinate regression approach leveraging a Transformer network to better utilize the spatial information in the feature map.

Face Alignment Face Recognition

Sub-pixel face landmarks using heatmaps and a bag of tricks

no code implementations • 4 Mar 2021 • Samuel W. F. Earp, Aubin Samacoits, Sanjana Jain, Pavit Noinongyao, Siwa Boonpunmongkol

We also show that it is possible to reduce the upscaling complexity by using a mixture of deconvolution and pixel-shuffle layers without impeding localization performance.

Face Alignment Face Recognition +1