A web application to create your own custom creatives (and much more).

Some GAN inversion methods I used or wrote before.

Repo for all the SRIP 2024 work at CVIG Lab IITGN under Prof. Shanmuganathan Raman

QC-StyleGAN - Quality Controllable Image Generation and Manipulation (NeurIPS 2022)

We use self-expressive layer to learn the affinity matrix of the hidden space of a generator, and we found subspace in GAN. Also we propsed a subspace-based high-fidelity GAN inversion model.

inverting an image back to its latent space Z

[NIPS2024] Official Code Repository for "Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images"

Official Implementation of "StylePrompter: All Styles Need Is Attention" [ACM MM 2023]

Python scripts to pre-train, fine-tune and use JoJoGAN with improved GAN inversion.

Official implementation of https://arxiv.org/pdf/2312.05330.pdf

Reference-Based 3D-Aware Image Editing with Triplanes

Author implementation of RiDDLE: Reversible and Diversified De-identification with Latent Encryptor (CVPR 2023)

This is a simple demo for "Modeling GAN Latent Dynamics using Neural ODEs".

A GAN inversion toolbox based on PyTorch library. We design a unified pipeline for inversion methods and conduct a comprehensive benchmark.

Official implementation of "Intra-Source Style Augmentation for Improved Domain Generalization" (WACV 2023 & IJCV)

[ECCV 2022] PadInv: High-fidelity GAN Inversion with Padding Space

[CVPR 2023] E3DGE: An encoder-based 3D StyleGAN inversion framework.

Collection of works in my PhD at Virginia Tech, mostly focused on computer vision and machine learning applications in structural inspection and structural health monitoring.

HyperInverter: Improving StyleGAN Inversion via Hypernetwork (CVPR 2022)