Over the last few decades, many aspects of human life have been enhanced with virtual domains, from the advent of digital assistants such as Amazon's Alexa and Apple's Siri to the latest metaverse efforts of the rebranded Meta. These trends underscore the importance of generating photorealistic visual depictions of humans. This has led to the rapid growth of so-called deepfake and talking-head generation methods in recent years. Despite their impressive results and popularity, they usually lack certain qualitative aspects such as texture quality, lips synchronization, or resolution, and practical aspects such as the ability to run in real-time. To allow for virtual human avatars to be used in practical scenarios, we propose an end-to-end framework for synthesizing high-quality virtual human faces capable of speaking with accurate lip motion with a special emphasis on performance. We introduce a novel network utilizing visemes as an intermediate audio representation and a novel data augmentation strategy employing a hierarchical image synthesis approach that allows disentanglement of the different modalities used to control the global head motion. Our method runs in real-time, and is able to deliver superior results compared to the current state-of-the-art.

Abstract We present a novel approach to the real‐time non‐photorealistic rendering of 3D models in which a single hand‐drawn exemplar specifies its appearance. We employ guided patch‐based synthesis to achieve high visual quality as well as temporal coherence. However, unlike previous techniques that maintain consistency in one dimension (temporal domain), in our approach, multiple dimensions are taken into account to cover all degrees of freedom given by the available space of interactions (e.g., camera rotations). To enable interactive experience, we precalculate a sparse latent representation of the entire interaction space, which allows rendering of a stylized image in real‐time, even on a mobile device. To the best of our knowledge, the proposed system is the first that enables interactive example‐based stylization of 3D models with full temporal coherence in predefined interaction space.

In this paper, we present a learning-based method to the keyframe-based video stylization that allows an artist to propagate the style from a few selected keyframes to the rest of the sequence. Its key advantage is that the resulting stylization is semantically meaningful, i.e., specific parts of moving objects are stylized according to the artist's intention. In contrast to previous style transfer techniques, our approach does not require any lengthy pre-training process nor a large training dataset. We demonstrate how to train an appearance translation network from scratch using only a few stylized exemplars while implicitly preserving temporal consistency. This leads to a video stylization framework that supports real-time inference, parallel processing, and random access to an arbitrary output frame. It can also merge the content from multiple keyframes without the need to perform an explicit blending operation. We demonstrate its practical utility in various interactive scenarios, where the user paints over a selected keyframe and sees her style transferred to an existing recorded sequence or a live video stream.

Abstract We present StyleBlit—an efficient example‐based style transfer algorithm that can deliver high‐quality stylized renderings in real‐time on a single‐core CPU. Our technique is especially suitable for style transfer applications that use local guidance ‐ descriptive guiding channels containing large spatial variations. Local guidance encourages transfer of content from the source exemplar to the target image in a semantically meaningful way. Typical local guidance includes, e.g., normal values, texture coordinates or a displacement field. Contrary to previous style transfer techniques, our approach does not involve any computationally expensive optimization. We demonstrate that when local guidance is used, optimization‐based techniques converge to solutions that can be well approximated by simple pixel‐level operations. Inspired by this observation, we designed an algorithm that produces results visually similar to, if not better than, the state‐of‐the‐art, and is several orders of magnitude faster. Our approach is suitable for scenarios with low computational budget such as games and mobile applications.

We introduce a new example-based approach to video stylization, with a focus on preserving the visual quality of the style, user controllability and applicability to arbitrary video. Our method gets as input one or more keyframes that the artist chooses to stylize with standard painting tools. It then automatically propagates the stylization to the rest of the sequence. To facilitate this while preserving visual quality, we developed a new type of guidance for state-of-art patch-based synthesis, that can be applied to any type of video content and does not require any additional information besides the video itself and a user-specified mask of the region to be stylized. We further show a temporal blending approach for interpolating style between keyframes that preserves texture coherence, contrast and high frequency details. We evaluate our method on various scenes from real production setting and provide a thorough comparison with prior art.