• Corpus ID: 245123601

HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture

  title={HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture},
  author={Ziyan Wang and Giljoo Nam and Tuur Stuyck and Stephen Lombardi and Michael Zollhoefer and Jessica Hodgins and Christoph Lassner},
Capturing and rendering life-like hair is particularly challenging due to its fine geometric structure, the complex physical interaction and its non-trivial visual appearance. Yet, hair is a critical component for believable avatars. In this paper, we address the aforementioned problems: 1) we use a novel, volumetric hair representation that is composed of thousands of primitives. Each primitive can be rendered efficiently, yet realistically, by building on the latest advances in neural… 


Mixture of volumetric primitives for efficient neural rendering
Mixture of Volumetric Primitives (MVP), a representation for rendering dynamic 3D content that combines the completeness of volumetric representations with the efficiency of primitive-based rendering, is presented.
Learning Compositional Radiance Fields of Dynamic Human Heads
This work proposes a novel compositional 3D representation that combines the best of previous methods to produce both higher-resolution and faster results and shows that the learned dynamic radiance field can be used to synthesize novel unseen expressions based on a global animation code.
Human Hair Inverse Rendering using Multi-View Photometric data
We introduce a hair inverse rendering framework to reconstruct high-fidelity 3D geometry of human hair, as well as its reflectance, which can be readily used for photorealistic rendering of hair. We
Deep appearance models for face rendering
A data-driven rendering pipeline that learns a joint representation of facial geometry and appearance from a multiview capture setup and a novel unsupervised technique for mapping images to facial states results in a system that is naturally suited to real-time interactive settings such as Virtual Reality (VR).
Multi-view hair capture using orientation fields
A multi-view hair reconstruction algorithm based on orientation fields with structure-aware aggregation that faithfully reconstructs detailed hair structures and is suitable for capturing hair in motion.
Hair photobooth: geometric and photometric acquisition of real hairstyles
A new reflectance interpolation technique is introduced that leverages an analytical reflectance model to alleviate cross-fading artifacts caused by linear methods and closely match the real hairstyles and can be used for animation.
Capture of hair geometry from multiple images
An image-based approach to capture the geometry of hair by drawing information from the scattering properties of the hair that are normally considered a hindrance and paves the way for a new approach to digital hair generation.
Volumetric Methods for Simulation and Rendering of Hair
This paper builds on the existing approaches to illumination and simulation by intr oducing a volumetric representation of hair which allows them to effici ently model collective properties of hair.
Strand-Accurate Multi-View Hair Capture
This paper presents the first method to capture high-fidelity hair geometry with strand-level accuracy and evaluates the method on both synthetic data and real captured data, showing that it can reconstruct hair strands with sub-millimeter accuracy.
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
The proposed Pixel-aligned Implicit Function (PIFu), an implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object, achieves state-of-the-art performance on a public benchmark and outperforms the prior work for clothed human digitization from a single image.