Related papers: MetaAvatar: Learning Animatable Clothed Human Mode…
Reconstructing 3D clothed human avatars from single images is a challenging task, especially when encountering complex poses and loose clothing. Current methods exhibit limitations in performance, largely attributable to their dependence on…
We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. Recent advances in neural rendering based reconstruction have achieved compelling results. However,…
The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic fake facial images, posing serious threats to personal privacy and the integrity of online information. Existing deepfake detection…
Current methods for learning realistic and animatable 3D clothed avatars need either posed 3D scans or 2D images with carefully controlled user poses. In contrast, our goal is to learn an avatar from only 2D images of people in…
Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. While 3D meshes enable efficient processing and are…
Avatar modelling has broad applications in human animation and virtual try-ons. Recent advancements in this field have focused on high-quality and comprehensive human reconstruction but often overlook the separation of clothing from the…
We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid…
A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D…
Realistic reconstruction of 3D clothing from an image has wide applications, such as avatar creation and virtual try-on. This paper presents a novel framework that reconstructs the texture map for 3D garments from a single image with pose.…
Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such…
We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence…
We present a novel method to learn Personalized Implicit Neural Avatars (PINA) from a short RGB-D sequence. This allows non-expert users to create a detailed and personalized virtual copy of themselves, which can be animated with realistic…
In this work we target a learnable output representation that allows continuous, high resolution outputs of arbitrary shape. Recent works represent 3D surfaces implicitly with a Neural Network, thereby breaking previous barriers in…
Metasurfaces have shown promising potentials in shaping optical wavefronts while remaining compact compared to bulky geometric optics devices. Design of meta-atoms, the fundamental building blocks of metasurfaces, relies on trial-and-error…
3D content creation is referred to as one of the most fundamental tasks of computer graphics. And many 3D modeling algorithms from 2D images or curves have been developed over the past several decades. Designers are allowed to align some…
Creating a controllable and relightable digital avatar from multi-view video with fixed illumination is a very challenging problem since humans are highly articulated, creating pose-dependent appearance effects, and skin as well as clothing…
We present a novel method for generating 3D garment deformations from given body poses, which is key to a wide range of applications, including virtual try-on and extended reality. To simplify the cloth dynamics, existing methods mostly…
We present Vid2Avatar, a method to learn human avatars from monocular in-the-wild videos. Reconstructing humans that move naturally from monocular in-the-wild videos is difficult. Solving it requires accurately separating humans from…
Dense 3D object reconstruction from a single image has recently witnessed remarkable advances, but supervising neural networks with ground-truth 3D shapes is impractical due to the laborious process of creating paired image-shape datasets.…
Efficiently digitizing high-fidelity animatable human avatars from videos is a challenging and active research topic. Recent volume rendering-based neural representations open a new way for human digitization with their friendly usability…