6 papers
Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
Rohit Chowdhury, Aniruddha Bala, Rohan Jaiswal +1
The rapid progress of image-to-video (I2V) generation models has introduced significant risks by enabling deceptive or malicious video synthesis from a single image. Prior defenses…
GalaxyEdit: Large-Scale Image Editing Dataset with Enhanced Diffusion Adapter
Aniruddha Bala, Rohan Jaiswal, Siddharth Roheda +2
Training of large-scale text-to-image and image-to-image models requires a huge amount of annotated data. While text-to-image datasets are abundant, data available for instruction-…
CART: Compositional Auto-Regressive Transformer for Image Generation
Siddharth Roheda, Rohit Chowdhury, Aniruddha Bala +1
We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved tran…
VNODE: A Piecewise Continuous Volterra Neural Network
Siddharth Roheda, Aniruddha Bala, Rohit Chowdhury +1
This paper introduces Volterra Neural Ordinary Differential Equations (VNODE), a piecewise continuous Volterra Neural Network that integrates nonlinear Volterra filtering with cont…
DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing
Aniruddha Bala, Rohit Chowdhury, Rohan Jaiswal +1
Advancements in diffusion models have enabled effortless image editing via text prompts, raising concerns about image security. Attackers with access to user images can exploit the…
LLVD: LSTM-based Explicit Motion Modeling in Latent Space for Blind Video Denoising
Loay Rashid, Siddharth Roheda, Amit Unde
Video restoration plays a pivotal role in revitalizing degraded video content by rectifying imperfections caused by various degradations introduced during capturing (sensor noise,…