Related papers: AvatarShield: Visual Reinforcement Learning for Hu…

Generating higher-resolution human-centric scenes with details and controls remains a challenge for existing text-to-image diffusion models. This challenge stems from limited training image size, text encoder capacity (limited tokens), and…

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…

The recent realistic creation and dissemination of so-called deepfakes poses a serious threat to social life, civil rest, and law. Celebrity defaming, election manipulation, and deepfakes as evidence in court of law are few potential…

The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the…

Artificial intelligence (AI) in media has advanced rapidly over the last decade. The introduction of Generative Adversarial Networks (GANs) improved the quality of photorealistic image generation. Diffusion models later brought a new era of…

Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework…

With recent generative models facilitating photo-realistic image synthesis, the proliferation of synthetic images has also engendered certain negative impacts on social platforms, thereby raising an urgent imperative to develop effective…

Large vision-language models have achieved remarkable capabilities by training on massive internet-scale data, yet a fundamental asymmetry persists: while LLMs can leverage self-supervised pretraining on abundant text and image data, the…

Virtual reality (VR) headsets provide an immersive, stereoscopic visual experience, but at the cost of blocking users from directly observing their physical environment. Passthrough techniques are intended to address this limitation by…

Human-centric visual tasks have attracted increasing research attention due to their widespread applications. In this paper, we aim to learn a general human representation from massive unlabeled human images which can benefit downstream…

The rapid surge of text-to-speech and face-voice reenactment models makes video fabrication easier and highly realistic. To encounter this problem, we require datasets that rich in type of generation methods and perturbation strategy which…

Text-driven large scene image synthesis has made significant progress with diffusion models, but controlling it is challenging. While using additional spatial controls with corresponding texts has improved the controllability of large scene…

The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While…

Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to…

We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of…

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to…

With the rapid development of deep learning techniques, the generation and counterfeiting of multimedia material are becoming increasingly straightforward to perform. At the same time, sharing fake content on the web has become so simple…

Detecting DeepFakes has become a crucial research area as the widespread use of AI image generators enables the effortless creation of face-manipulated and fully synthetic content, while existing methods are often limited to binary…

Although recent text-to-video generative models are getting more capable of following external camera controls, imposed by either text descriptions or camera trajectories, they still struggle to generalize to unconventional camera motions,…

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the…