Related papers: Silence is Golden: Leveraging Adversarial Examples…

Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this…

Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector control found in GANs,…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remove or filter…

All previous methods for audio-driven talking head generation assume the input audio to be clean with a neutral tone. As we show empirically, one can easily break these systems by simply adding certain background noise to the utterance or…

Text-to-image generative models have made remarkable advancements in generating high-quality images. However, generated images often contain undesirable artifacts or other errors due to model limitations. Existing techniques to fine-tune…

Audio-Driven Talking Face Generation aims at generating realistic videos of talking faces, focusing on accurate audio-lip synchronization without deteriorating any identity-related visual details. Recent state-of-the-art methods are based…

With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, their multimodal nature…

The success of deep learning based face recognition systems has given rise to serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Existing methods for enhancing privacy fail to…

Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes…

Face animation has achieved much progress in computer vision. However, prevailing GAN-based methods suffer from unnatural distortions and artifacts due to sophisticated motion deformation. In this paper, we propose a Face Animation…

Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. However, there is significant concern about the potential misuse…

Latent Video Diffusion Models (LVDMs) have achieved state-of-the-art generative quality for image and video generation; however, they remain brittle under noisy conditioning, where small perturbations in text or multimodal embeddings can…

The pose-guided person image generation task requires synthesizing photorealistic images of humans in arbitrary poses. The existing approaches use generative adversarial networks that do not necessarily maintain realistic textures or need…

The growing use of portrait images in computer vision highlights the need to protect personal identities. At the same time, anonymized images must remain useful for downstream computer vision tasks. In this work, we propose a unified…

Animating virtual avatars to make co-speech gestures facilitates various applications in human-machine interaction. The existing methods mainly rely on generative adversarial networks (GANs), which typically suffer from notorious mode…

Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial…

Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A…

As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems.…