Related papers: MonoHuman: Animatable Human Neural Field from Mono…
Recent advances in Neural Radiance Fields (NeRFs) have made it possible to reconstruct and reanimate dynamic portrait scenes with control over head-pose, facial expressions and viewing direction. However, training such models assumes…
We introduce FlexAvatar, a method for creating high-quality and complete 3D head avatars from a single image. A core challenge lies in the limited availability of multi-view data and the tendency of monocular training to yield incomplete 3D…
We present InstantGeoAvatar, a method for efficient and effective learning from monocular video of detailed 3D geometry and appearance of animatable implicit human avatars. Our key observation is that the optimization of a hash grid…
Face rendering using neural radiance fields (NeRF) is a rapidly developing research area in computer vision. While recent methods primarily focus on controlling facial attributes such as identity and expression, they often overlook the…
Monocular depth estimation has applications in many fields, such as autonomous navigation and extended reality, making it an essential computer vision task. However, current methods often produce smooth depth maps that lack the fine…
An increasingly common approach for creating photo-realistic digital avatars is through the use of volumetric neural fields. The original neural radiance field (NeRF) allowed for impressive novel view synthesis of static heads when trained…
Monocular 3D human performance capture is indispensable for many applications in computer graphics and vision for enabling immersive experiences. However, detailed capture of humans requires tracking of multiple aspects, including the…
Neural Radiance Fields (NeRF), initially developed for static scenes, have inspired many video novel view synthesis techniques. However, the challenge for video view synthesis arises from motion blur, a consequence of object or camera…
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or…
We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields involves optimizing the representation…
We have recently seen tremendous progress in the neural advances for photo-real human modeling and rendering. However, it's still challenging to integrate them into an existing mesh-based pipeline for downstream applications. In this paper,…
We address the problem of photorealistic 3D face avatar synthesis from sparse images. Existing Parametric models for face avatar reconstruction struggle to generate details that originate from inputs. Meanwhile, although current NeRF-based…
Photorealistic 3D head avatars are vital for telepresence, gaming, and VR. However, most methods focus solely on facial regions, ignoring natural hand-face interactions, such as a hand resting on the chin or fingers gently touching the…
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or…
Neural radiance field (NeRF) has become a popular 3D representation method for human avatar reconstruction due to its high-quality rendering capabilities, e.g., regarding novel views and poses. However, previous methods for editing the…
Dynamic radiance fields have emerged as a promising approach for generating novel views from a monocular video. However, previous methods enforce the geometric consistency to dynamic radiance fields only between adjacent input frames,…
We present a novel framework to reconstruct complete 3D human shapes from a given target image by leveraging monocular unconstrained images. The objective of this work is to reproduce high-quality details in regions of the reconstructed…
Given a monocular video, segmenting and decoupling dynamic objects while recovering the static environment is a widely studied problem in machine intelligence. Existing solutions usually approach this problem in the image domain, limiting…
We present the first method to capture the 3D total motion of a target person from a monocular view input. Given an image or a monocular video, our method reconstructs the motion from body, face, and fingers represented by a 3D deformable…
To address the ill-posed problem caused by partial observations in monocular human volumetric capture, we present AvatarCap, a novel framework that introduces animatable avatars into the capture pipeline for high-fidelity reconstruction in…