no code implementations • 22 Dec 2023 • Snehal Singh Tomar, A. N. Rajagopalan
Consequentially, style editing of the chosen ROIs amounts to a simple combination of (a) the ROI-mask generated from the sliced structure representation and (b) the decoded image with global style changes, generated from the manipulated (using Gaussian noise) global style and unchanged structure tensor.
no code implementations • 21 Nov 2022 • Snehal Singh Tomar, Maitreya Suin, A. N. Rajagopalan
Both inversion of real images and determination of controllable latent directions are computationally expensive operations.
no code implementations • 20 Nov 2022 • Snehal Singh Tomar, Maitreya Suin, A. N. Rajagopalan
Our model fuses per-pixel local information learned using two fully convolutional depth encoders with global contextual information learned by a transformer encoder at different scales.
no code implementations • 5 Jul 2022 • Snehal Singh Tomar, A. N. Rajagopalan
Our endeavour in this work is to do away with the priors and complex pre-processing operations required by SOTA multi-class face segmentation models by reframing this operation as a downstream task post infusion of disentanglement with respect to facial semantic regions of interest (ROIs) in the latent space of a Generative Autoencoder model.