Related papers: LatentAvatar: Learning Latent Expression Code for …
While recent research has made significant progress in speech-driven talking face generation, the quality of the generated video still lags behind that of real recordings. One reason for this is the use of handcrafted intermediate…
Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable entities remains challenging. The generic reconstruction methods…
We propose a method for synthesizing photo-realistic digital avatars from only one portrait as the reference. Given a portrait, our method synthesizes a coarse talking head video using driving keypoints features. And with the coarse video,…
In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically…
This study explores a streamlined facial data collection method for conversational contexts, addressing the limitations of existing approaches that often require extensive datasets and prioritize technical metrics over user perception and…
Blind face restoration from low-quality (LQ) images is a challenging task that requires not only high-fidelity image reconstruction but also the preservation of facial identity. While diffusion models like Stable Diffusion have shown…
Real-time and robust photorealistic avatars for telepresence in AR/VR have been highly desired for enabling immersive photorealistic telepresence. However, there still exists one key bottleneck: the considerable computational expense needed…
Recent advances in high-fidelity semantic image editing heavily rely on the presumably disentangled latent spaces of the state-of-the-art generative models, such as StyleGAN. Specifically, recent works show that it is possible to achieve…
Acquisition and rendering of photo-realistic human heads is a highly challenging research problem of particular importance for virtual telepresence. Currently, the highest quality is achieved by volumetric approaches trained in a person…
Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications. Existing methods are either limited to rigid object modeling, or not…
Producing expressive facial animations from static images is a challenging task. Prior methods relying on explicit geometric priors (e.g., facial landmarks or 3DMM) often suffer from artifacts in cross reenactment and struggle to capture…
We propose an approach to generate images of people given a desired appearance and pose. Disentangled representations of pose and appearance are necessary to handle the compound variability in the resulting generated images. Hence, we…
Despite significant progress in 3D avatar reconstruction, it still faces challenges such as high time complexity, sensitivity to data quality, and low data utilization. We propose FastAvatar, a feedforward 3D avatar framework capable of…
Understanding the neural implementation of complex human behaviors is one of the major goals in neuroscience. To this end, it is crucial to find a true representation of the neural data, which is challenging due to the high complexity of…
We propose a simple yet powerful Landmark guided Generative Adversarial Network (LandmarkGAN) for the facial expression-to-expression translation using a single image, which is an important and challenging task in computer vision since the…
Learning an animatable and clothed human avatar model with vivid dynamics and photorealistic appearance from multi-view videos is an important foundational research problem in computer graphics and vision. Fueled by recent advances in…
A photorealistic and immersive human avatar experience demands capturing fine, person-specific details such as cloth and hair dynamics, subtle facial expressions, and characteristic motion patterns. Achieving this requires large,…
Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3D scene as a continuous function. Though NeRF is able to render complex 3D scenes with view-dependent effects, few efforts have been devoted to exploring its…
We present Dynamic Neural Portraits, a novel approach to the problem of full-head reenactment. Our method generates photo-realistic video portraits by explicitly controlling head pose, facial expressions and eye gaze. Our proposed…
Face reenactment is challenging due to the need to establish dense correspondence between various face representations for motion transfer. Recent studies have utilized Neural Radiance Field (NeRF) as fundamental representation, which…