Related papers: Efficient Meshy Neural Fields for Animatable Human…
The ability to create realistic, animatable and relightable head avatars from casual video sequences would open up wide ranging applications in communication and entertainment. Current methods either build on explicit 3D morphable meshes…
Speech-driven gestures and facial animations are fundamental to expressive digital avatars in games, virtual production, and interactive media. However, existing methods are either limited to a single modality for audio motion alignment,…
Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated the remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8 hours), which…
Digital human animation relies on high-quality 3D models of the human face: rigs. A face rig must be accurate and, at the same time, fast to compute. One of the most common rigging models is the blendshape model. We propose a novel…
Visualizing a large-scale volumetric dataset with high resolution is challenging due to the substantial computational time and space complexity. Recent deep learning-based image inpainting methods significantly improve rendering latency by…
Faithful real-time facial animation is essential for avatar-mediated telepresence in Virtual Reality (VR). To emulate authentic communication, avatar animation needs to be efficient and accurate: able to capture both extreme and subtle…
Constructing drivable and photorealistic 3D head avatars has become a central task in AR/XR, enabling immersive and expressive user experiences. With the emergence of high-fidelity and efficient representations such as 3D Gaussians, recent…
Over the past few years, the automatic generation of facial animation for virtual characters has garnered interest among the animation research and industry communities. Recent research contributions leverage machine-learning approaches to…
We present an elastic simulator for domains defined as evolving implicit functions, which is efficient, robust, and differentiable with respect to both shape and material. This simulator is motivated by applications in 3D reconstruction: it…
We present HumanNeRF-SE, a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead, we reload these…
Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…
Creating realistic virtual assets is a time-consuming process: it usually involves an artist designing the object, then spending a lot of effort on tweaking its appearance. Intricate details and certain effects, such as subsurface…
We present X-Avatar, a novel avatar model that captures the full expressiveness of digital humans to bring about life-like experiences in telepresence, AR/VR and beyond. Our method models bodies, hands, facial expressions and appearance in…
Unsupervised generation of 3D-aware clothed humans with various appearances and controllable geometries is important for creating virtual human avatars and other AR/VR applications. Existing methods are either limited to rigid object…
Evolutionary artificial neural networks (EANNs) refer to a special class of artificial neural networks (ANNs) in which evolution is another fundamental form of adaptation in addition to learning. Evolutionary algorithms are used to adapt…
Reconstructing personalized animatable head avatars has significant implications in the fields of AR/VR. Existing methods for achieving explicit face control of 3D Morphable Models (3DMM) typically rely on multi-view images or videos of a…
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…
It is now possible to reconstruct dynamic human motion and shape from a sparse set of cameras using Neural Radiance Fields (NeRF) driven by an underlying skeleton. However, a challenge remains to model the deformation of cloth and skin in…
In this paper, we introduce FitMe, a facial reflectance model and a differentiable rendering optimization pipeline, that can be used to acquire high-fidelity renderable human avatars from single or multiple images. The model consists of a…
Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the large memory overhead…