相关论文: Dormant: Defending against Pose-driven Human Image…

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image…

We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical…

Expressive human pose and shape estimation (EHPS) plays a central role in digital human generation, particularly in live-streaming applications. However, most existing EHPS models focus primarily on minimizing estimation errors, with…

As 3D human pose estimation can now be achieved with very high accuracy in the supervised learning scenario, tackling the case where 3D pose annotations are not available has received increasing attention. In particular, several methods…

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…

Controllable human image animation aims to generate videos from reference images using driving videos. Due to the limited control signals provided by sparse guidance (e.g., skeleton pose), recent works have attempted to introduce additional…

Pose-guided video generation has become a powerful tool in creative industries, exemplified by frameworks like Animate Anyone. However, conditioning generation on specific poses introduces serious risks, such as impersonation, privacy…

We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photorealistic images of full-body humans with consistent appearances under different view-angles and body-poses. To tackle the representational and…

With the increasing prevalence of diffusion-based malicious image manipulation, existing proactive defense methods struggle to safeguard images against tampering under unknown conditions. To address this, we propose Anti-Inpainting, a…

Images, captured by a camera, play a critical role in training Deep Neural Networks (DNNs). Usually, we assume the images acquired by cameras are consistent with the ones perceived by human eyes. However, due to the different physical…

Recent pose-transfer methods aim to generate temporally consistent and fully controllable videos of human action where the motion from a reference video is reenacted by a new identity. We evaluate three state-of-the-art pose-transfer…

Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…

Photo-realistic re-rendering of a human from a single image with explicit control over body pose, shape and appearance enables a wide range of applications, such as human appearance transfer, virtual try-on, motion imitation, and novel view…

3D animation of humans in action is quite challenging as it involves using a huge setup with several motion trackers all over the person's body to track the movements of every limb. This is time-consuming and may cause the person discomfort…

Face manipulation methods can be misused to affect an individual's privacy or to spread disinformation. To this end, we introduce a novel data-driven approach that produces image-specific perturbations which are embedded in the original…

The DeepFakes, which are the facial manipulation techniques, is the emerging threat to digital society. Various DeepFake detection methods and datasets are proposed for detecting such data, especially for face-swapping. However, recent…

We propose a method to estimate 3D human poses from substantially blurred images. The key idea is to tackle the inverse problem of image deblurring by modeling the forward problem with a 3D human model, a texture map, and a sequence of…

Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also…

Most monocular and physics-based human pose tracking methods, while achieving state-of-the-art results, suffer from artifacts when the scene does not have a strictly flat ground plane or when the camera is moving. Moreover, these methods…

Neural networks build the foundation of several intelligent systems, which, however, are known to be easily fooled by adversarial examples. Recent advances made these attacks possible even in air-gapped scenarios, where the autonomous…