-
The University of Texas at Austin
- Austin
-
09:24
(UTC -05:00) - https://krishnasrikard.github.io/
- in/krishna-srikar-durbha
Highlights
- Pro
Pinned Loading
-
Perceptual-Classifiers-Detecting-Generative-Images-using-Perceptual-Features
Perceptual-Classifiers-Detecting-Generative-Images-using-Perceptual-Features PublicHere, we leverage the capabilities of existing IQA models, which effectively capture the manifold of real images within a bandpass statistical space, to distinguish between real and AI-generated im…
Python 2
-
Constructing-Per-Shot-Bitrate-Ladders-using-Visual-Information-Fidelity
Constructing-Per-Shot-Bitrate-Ladders-using-Visual-Information-Fidelity PublicWe develop a perceptually optimized method of constructing optimal per-shot bitrate and quality ladders, using an ensemble of low-level features and Visual Information Fidelity (VIF) features extra…
Python 2
-
SR-DDPM
SR-DDPM PublicForked from shreshthsaini/SR-DDPM
Denoising diffusion probabilistic model for low level vision task. Developing a novel DM for super resolution task; later to be extended for general vision tasks such as deblurring, dehazing, rain …
Jupyter Notebook
-
Optical-Flow-Less-Video-Frame-Interpolation
Optical-Flow-Less-Video-Frame-Interpolation PublicA modified light weight VRT is used to predict intermediate frames by looking only the previous frames or following causality without any use optical flow estimation techniques.
Python 1
-
White-Box-Cartoonization
White-Box-Cartoonization PublicExperiments with two different models mainly VGG19 and VIT-16 which are used for calculating Structure and Content Losses in White Box Cartoonization and understanding the performance of the cartoo…
Python 1
-
AutoML-Models-for-Wireless-Signals-Classification-and-effectiveness-against-Adversarial-Attacks
AutoML-Models-for-Wireless-Signals-Classification-and-effectiveness-against-Adversarial-Attacks PublicComparing and understanding the performance of AutoML models with state-of-the-art models on wireless signal classification and their vulnerability towards transfer-based Projected Gradient Descent…
If the problem persists, check the GitHub status page or contact support.