Reconstructing Animatable Categories from Videos

Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging, which are difficult to scale to arbitrary categories. Recently, differentiable rendering provides a pathway to obtain high-quality 3D models from monocular videos, but these are lim...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-05
Main Authors: Yang, Gengshan, Wang, Chaoyang, Reddy, N Dinesh, Ramanan, Deva
Format: Article
Language:English
Subjects:
Categories
Optimization
Regularization
Rigging
Three dimensional models
Video
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging, which are difficult to scale to arbitrary categories. Recently, differentiable rendering provides a pathway to obtain high-quality 3D models from monocular videos, but these are limited to rigid categories or single instances. We present RAC that builds category 3D models from monocular videos while disentangling variations over instances and motion over time. Three key ideas are introduced to solve this problem: (1) specializing a skeleton to instances via optimization, (2) a method for latent space regularization that encourages shared structure across a category while maintaining instance details, and (3) using 3D background models to disentangle objects from the background. We show that 3D models of humans, cats, and dogs can be learned from 50-100 internet videos.
ISSN:2331-8422