Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shetty, Ashwath, Habermann, Marc, Sun, Guoxing, Luvizon, Diogo, Golyanik, Vladislav, Theobalt, Christian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910540566102016
author Shetty, Ashwath
Habermann, Marc
Sun, Guoxing
Luvizon, Diogo
Golyanik, Vladislav
Theobalt, Christian
author_facet Shetty, Ashwath
Habermann, Marc
Sun, Guoxing
Luvizon, Diogo
Golyanik, Vladislav
Theobalt, Christian
contents We present the first approach to render highly realistic free-viewpoint videos of a human actor in general apparel, from sparse multi-view recording to display, in real-time at an unprecedented 4K resolution. At inference, our method only requires four camera views of the moving actor and the respective 3D skeletal pose. It handles actors in wide clothing, and reproduces even fine-scale dynamic detail, e.g. clothing wrinkles, face expressions, and hand gestures. At training time, our learning-based approach expects dense multi-view video and a rigged static surface scan of the actor. Our method comprises three main stages. Stage 1 is a skeleton-driven neural approach for high-quality capture of the detailed dynamic mesh geometry. Stage 2 is a novel solution to create a view-dependent texture using four test-time camera views as input. Finally, stage 3 comprises a new image-based refinement network rendering the final 4K image given the output from the previous stages. Our approach establishes a new benchmark for real-time rendering resolution and quality using sparse input camera views, unlocking possibilities for immersive telepresence.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07423
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras
Shetty, Ashwath
Habermann, Marc
Sun, Guoxing
Luvizon, Diogo
Golyanik, Vladislav
Theobalt, Christian
Computer Vision and Pattern Recognition
We present the first approach to render highly realistic free-viewpoint videos of a human actor in general apparel, from sparse multi-view recording to display, in real-time at an unprecedented 4K resolution. At inference, our method only requires four camera views of the moving actor and the respective 3D skeletal pose. It handles actors in wide clothing, and reproduces even fine-scale dynamic detail, e.g. clothing wrinkles, face expressions, and hand gestures. At training time, our learning-based approach expects dense multi-view video and a rigged static surface scan of the actor. Our method comprises three main stages. Stage 1 is a skeleton-driven neural approach for high-quality capture of the detailed dynamic mesh geometry. Stage 2 is a novel solution to create a view-dependent texture using four test-time camera views as input. Finally, stage 3 comprises a new image-based refinement network rendering the final 4K image given the output from the previous stages. Our approach establishes a new benchmark for real-time rendering resolution and quality using sparse input camera views, unlocking possibilities for immersive telepresence.
title Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.07423